Skills/PyPI/injection-pii-guardrail-mcp

injection-pii-guardrail-mcp@0.1.2

CAUTION

Publisher claims: "An MCP server providing prompt-injection detection, PII/secrets redaction, and an audit trail for AI agents." Observed in sandbox: static analysis only — behavior not yet observed.

Registry PyPI (MCP server)Publisher ss-2303 · joined 0 days agoInstalls 21Last detonated 2 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-04 and scored it 57/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompt injection attempt; Prompt injection; Prompt injection attempt. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

CRITICAL
Prompt injection attemptREADME.md:238 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionREADME.md:237 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptREADME.md:106 · Prompt injection attempt — 'ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptREADME.md:236 · Prompt injection attempt — 'ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionREADME.md:247 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attempteval/eval_set.json:25 · Prompt injection attempt — model control tokensFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
CRITICAL
Prompt injection attempteval/eval_set.json:12 · Prompt injection attempt — 'ignore previous instructions'Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
CRITICAL
Prompt injection attempteval/eval_set.json:27 · Prompt injection attempt — model control tokensFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
CRITICAL
Fake instruction boundary tagREADME.md:238 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injection attempteval/eval_set.json:28 · Prompt injection attempt — model control tokensFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
HIGH
Authorization escalation languageeval/eval_set.json:25 · Authorization escalation languageFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
GitHub token pattern detectedtests/test_detectors.py:115 · GitHub token pattern detected — possible hardcoded or harvested tokenFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
AWS access key pattern detectedtests/test_detectors.py:169 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Authorization escalation languageeval/eval_set.json:22 · Authorization escalation languageFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
AWS access key pattern detectedtests/test_detectors.py:109 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Authorization escalation languageREADME.md:237 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tageval/eval_set.json:26 · Fake instruction boundary tagFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
CRITICAL
Prompt injectioneval/eval_set.json:19 · Prompt injection — known jailbreak technique referenceFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
HIGH
Authorization escalation languageeval/eval_set.json:50 · Authorization escalation languageFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
AWS access key pattern detectedtests/test_mcp_client.py:33 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Role reassignment attempteval/eval_set.json:21 · Role reassignment attemptFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01

What would make this Verified

23 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim ss-2303: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. GitHub token pattern detected≈ +2 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
  4. AWS access key pattern detected≈ +2 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ss-2303