Skills/Claude Code plugins/aws-startup-advisor

aws-startup-advisor@2.0.3

CAUTION

Publisher claims: "Personalized AWS guidance built on patterns from 350,000+ startups. Get architecture, cost, and security recommendations matched to your stage, from day-one account setup to production-ready infrastructure. Migrate to AWS from Azure, GCP, or Heroku with resource discovery, cost estimates, and generated Terraform. Move OpenAI, Azure OpenAI, and Gemini code to Amazon Bedrock, and plan and prototype AI agents on AgentCore and other AWS runtimes. Includes AWS Activate credits eligibility, 60+ exclus" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Claude Code plugin marketplacePublisher aws · joined 0 days agoInstalls 0Last detonated 3 h ago
Dispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-26 and scored it 53/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; npx invocation of non-well-known package; Destructive file system command detected. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only

Static findings

HIGH
Access to sensitive file pathscommands/usage-data.md:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05
HIGH
npx invocation of non-well-known packageREADME.md:159 · npx invocation of non-well-known package — may execute untrusted code
AST06
CRITICAL
Destructive file system command detectedagents/llm2bedrock-code-rewriter.md:459 · Destructive file system command detected
AST05
CRITICAL
Prompt injection attemptagents/generic-phase-worker-rw.md:40 · Prompt injection attempt — 'ignore previous instructions'
AST01
CRITICAL
Rule modification attemptskills/shared/ai/ai-model-lifecycle.md:50 · Rule modification attempt — overwriting existing instructions
AST01
HIGH
Access to sensitive file pathsagents/llm2bedrock-code-rewriter.md:186 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05
HIGH
Access to sensitive file pathsagents/llm2bedrock-code-rewriter.md:566 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05
CRITICAL
Prompt injection attemptagents/llm2bedrock-code-rewriter.md:14 · Prompt injection attempt — 'ignore previous instructions'
AST01
CRITICAL
Destructive file system command detectedagents/llm2bedrock-code-rewriter.md:848 · Destructive file system command detected
AST05
CRITICAL
Rule modification attemptskills/shared/ai/ai-model-lifecycle.md:54 · Rule modification attempt — overwriting existing instructions
AST01
HIGH
npx invocation of non-well-known packageagents/llm2bedrock-code-rewriter.md:886 · npx invocation of non-well-known package — may execute untrusted code
AST06
HIGH
Access to sensitive file pathsagents/llm2bedrock-code-analyzer.md:157 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05
HIGH
Access to sensitive file pathsagents/llm2bedrock-code-rewriter.md:70 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05
HIGH
Access to sensitive file pathsagents/llm2bedrock-report-generator.md:745 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05
CRITICAL
Destructive file system command detectedagents/llm2bedrock-report-generator.md:648 · Destructive file system command detected
AST05
HIGH
Access to sensitive file pathsagents/llm2bedrock-code-rewriter.md:427 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05
CRITICAL
Prompt injection attemptagents/llm2bedrock-prompt-evaluator.md:24 · Prompt injection attempt — 'ignore previous instructions'
AST01
HIGH
npx invocation of non-well-known packageagents/llm2bedrock-code-rewriter.md:779 · npx invocation of non-well-known package — may execute untrusted code
AST06
CRITICAL
Prompt injection attemptagents/generic-phase-worker-rwx.md:73 · Prompt injection attempt — 'ignore previous instructions'
AST01
HIGH
Access to sensitive file pathsagents/llm2bedrock-code-rewriter.md:407 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05
CRITICAL
Prompt injection attemptagents/llm2bedrock-log-ingestor.md:22 · Prompt injection attempt — 'ignore previous instructions'
AST01
HIGH
npx invocation of non-well-known packageREADME.md:68 · npx invocation of non-well-known package — may execute untrusted code
AST06
CRITICAL
Rule modification attemptskills/shared/ai/ai-model-lifecycle.md:61 · Rule modification attempt — overwriting existing instructions
AST01
CRITICAL
Fake instruction boundary tagagents/llm2bedrock-prompt-evaluator.md:267 · Fake instruction boundary tag
AST01
CRITICAL
Destructive file system command detectedagents/llm2bedrock-log-ingestor.md:135 · Destructive file system command detected
AST05
CRITICAL
Prompt injection attemptagents/llm2bedrock-code-analyzer.md:21 · Prompt injection attempt — 'ignore previous instructions'
AST01
HIGH
Python subprocess execution detectedscripts/telemetry/test/test_consent.py:502 · Python subprocess execution detected
AST05
HIGH
Access to sensitive file pathsskills/shared/telemetry/PROTOCOL.md:43 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05
MEDIUM
File type combined with upload actionagents/generic-phase-worker-rwx.md:60 · File type combined with upload action — agent may exfiltrate local data files
AST07
HIGH
npx invocation of non-well-known packageskills/heroku-to-aws/SKILL.md:12 · npx invocation of non-well-known package — may execute untrusted code
AST06
HIGH
Access to sensitive file pathsscripts/telemetry/consent/record.py:4 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05
HIGH
Python subprocess execution detectedscripts/telemetry/test/test_consent.py:580 · Python subprocess execution detected
AST05
HIGH
Access to sensitive file pathsskills/operate-on-aws/SKILL.md:93 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05
HIGH
Access to sensitive file pathsscripts/telemetry/PROTOCOL.md:43 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05
HIGH
Python subprocess execution detectedscripts/telemetry/test/conftest.py:38 · Python subprocess execution detected
AST05
HIGH
Outbound HTTP to raw IP addressscripts/telemetry/test/test_migration.py:336 · Outbound HTTP to raw IP address — may bypass domain-based monitoring
AST07
MEDIUM
File type combined with upload actionREADME.md:42 · File type combined with upload action — agent may exfiltrate local data files
AST07
HIGH
Python subprocess execution detectedscripts/telemetry/test/test_consent.py:468 · Python subprocess execution detected
AST05
HIGH
Refusal suppressionskills/operate-on-aws/SKILL.md:282 · Refusal suppression — attempting to prevent safety responses
AST01
MEDIUM
File type combined with upload actionagents/llm2bedrock-log-ingestor.md:95 · File type combined with upload action — agent may exfiltrate local data files
AST07
HIGH
Process kill commandscripts/emit-plan-json.py:629 · Process kill command — agent can terminate processes
AST05
HIGH
Access to sensitive file pathsscripts/telemetry/README.md:11 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05
HIGH
Python subprocess execution detectedscripts/check-bedrock-pricing-parity.py:49 · Python subprocess execution detected
AST05
HIGH
npx invocation of non-well-known packageskills/operate-on-aws/SKILL.md:459 · npx invocation of non-well-known package — may execute untrusted code
AST06
HIGH
Python subprocess execution detectedscripts/telemetry/test/test_migration.py:106 · Python subprocess execution detected
AST05
HIGH
Python subprocess execution detectedscripts/telemetry/test/test_migration.py:735 · Python subprocess execution detected
AST05
HIGH
File permission modification commandskills/llm-to-bedrock/SKILL.md:754 · File permission modification command — agent changes file ownership/permissions
AST05
HIGH
Python subprocess execution detectedscripts/telemetry/test/test_cli.py:26 · Python subprocess execution detected
AST05
MEDIUM
File type combined with upload actionagents/llm2bedrock-log-ingestor.md:96 · File type combined with upload action — agent may exfiltrate local data files
AST07
HIGH
Access to sensitive file pathsscripts/telemetry/README.md:36 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05
HIGH
Outbound HTTP to raw IP addressscripts/telemetry/test/conftest.py:89 · Outbound HTTP to raw IP address — may bypass domain-based monitoring
AST07
HIGH
Process kill commandscripts/telemetry/test/test_consent.py:459 · Process kill command — agent can terminate processes
AST05
HIGH
npx invocation of non-well-known packageskills/llm-to-bedrock/SKILL.md:17 · npx invocation of non-well-known package — may execute untrusted code
AST06
HIGH
npx invocation of non-well-known packageskills/llm-to-bedrock/SKILL.md:86 · npx invocation of non-well-known package — may execute untrusted code
AST06
HIGH
npx invocation of non-well-known packageskills/knowledge-base-for-startups/SKILL.md:99 · npx invocation of non-well-known package — may execute untrusted code
AST06
HIGH
npx invocation of non-well-known packageskills/llm-to-bedrock/SKILL.md:115 · npx invocation of non-well-known package — may execute untrusted code
AST06
HIGH
Python subprocess execution detectedscripts/telemetry/test/test_cli.py:237 · Python subprocess execution detected
AST05
HIGH
npx invocation of non-well-known packageskills/llm-to-bedrock/SKILL.md:101 · npx invocation of non-well-known package — may execute untrusted code
AST06
MEDIUM
File type combined with upload actionagents/llm2bedrock-code-analyzer.md:357 · File type combined with upload action — agent may exfiltrate local data files
AST07
HIGH
npx invocation of non-well-known packageskills/prompt-library-for-startups/SKILL.md:120 · npx invocation of non-well-known package — may execute untrusted code
AST06
MEDIUM
File type combined with upload actionagents/llm2bedrock-report-generator.md:188 · File type combined with upload action — agent may exfiltrate local data files
AST07
HIGH
File permission modification commandskills/llm-to-bedrock/SKILL.md:764 · File permission modification command — agent changes file ownership/permissions
AST05
MEDIUM
File type combined with upload actionagents/llm2bedrock-log-ingestor.md:218 · File type combined with upload action — agent may exfiltrate local data files
AST07
HIGH
Python subprocess execution detectedscripts/telemetry/test/test_consent.py:492 · Python subprocess execution detected
AST05
HIGH
Python subprocess execution detectedscripts/telemetry/test/test_consent.py:567 · Python subprocess execution detected
AST05
HIGH
npx invocation of non-well-known packageskills/llm-to-bedrock/SKILL.md:117 · npx invocation of non-well-known package — may execute untrusted code
AST06
MEDIUM
File type combined with upload actionskills/heroku-to-aws/SKILL.md:220 · File type combined with upload action — agent may exfiltrate local data files
AST07
MEDIUM
URL using raw IP addressscripts/telemetry/test/conftest.py:89 · URL using raw IP address — may bypass domain-based filtering
AST07
MEDIUM
File type combined with upload actionscripts/telemetry/README.md:107 · File type combined with upload action — agent may exfiltrate local data files
AST07
MEDIUM
File type combined with upload actionagents/llm2bedrock-report-generator.md:205 · File type combined with upload action — agent may exfiltrate local data files
AST07
MEDIUM
File type combined with upload actionskills/gcp-to-aws/SKILL.md:60 · File type combined with upload action — agent may exfiltrate local data files
AST07
MEDIUM
File type combined with upload actionskills/heroku-to-aws/SKILL.md:228 · File type combined with upload action — agent may exfiltrate local data files
AST07
MEDIUM
File type combined with upload actionscripts/telemetry/test/test_migration.py:554 · File type combined with upload action — agent may exfiltrate local data files
AST07
MEDIUM
File type combined with upload actionskills/heroku-to-aws/SKILL.md:3 · File type combined with upload action — agent may exfiltrate local data files
AST07
MEDIUM
File type combined with upload actionskills/heroku-to-aws/SKILL.md:118 · File type combined with upload action — agent may exfiltrate local data files
AST07
MEDIUM
File type combined with upload actionskills/gcp-to-aws/SKILL.md:253 · File type combined with upload action — agent may exfiltrate local data files
AST07
MEDIUM
File type combined with upload actionskills/llm-to-bedrock/SKILL.md:358 · File type combined with upload action — agent may exfiltrate local data files
AST07
MEDIUM
File type combined with upload actionskills/heroku-to-aws/SKILL.md:145 · File type combined with upload action — agent may exfiltrate local data files
AST07
MEDIUM
URL using raw IP addressscripts/telemetry/test/test_migration.py:336 · URL using raw IP address — may bypass domain-based filtering
AST07
MEDIUM
File type combined with upload actionskills/agent-advisor/SKILL.md:122 · File type combined with upload action — agent may exfiltrate local data files
AST07
MEDIUM
File type combined with upload actionskills/gcp-to-aws/SKILL.md:379 · File type combined with upload action — agent may exfiltrate local data files
AST07
MEDIUM
File type combined with upload actionskills/gcp-to-aws/SKILL.md:376 · File type combined with upload action — agent may exfiltrate local data files
AST07