Skills/PyPI/daily-news-mcp

daily-news-mcp@0.1.2

CAUTION

Publisher claims: "MCP server exposing the Daily News engine (fetch, curate, rewrite AI/news) as tools." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher vinay-kumar-godavarti · joined 5 days agoInstalls 0Last detonated 5d ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-29 and scored it 60/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: System prompt continuation; Access to sensitive file paths; Prompt injection. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1
0.1sprocessexec /usr/bin/timeout
0.1sprocessexec .venv/bin/daily-news-mcp
0.1sprocessexited 127: timeout: failed to run command '.venv/bin/daily-news-mcp': No such file or directory
0.1sclaimedno tools/list reply (exit 127)
0.1sprocessscript backend runs setup only

Static findings

CRITICAL
System prompt continuationClaude.md:9 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsconfig.py:22 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Prompt injectionevals/golden/2026-09-18/sources.json:179 · 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
Access to sensitive file pathsmain.py:10 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Zero-width characters (hidden text)sources/base.py:34 · Zero-width characters (hidden text)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsconfig.py:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
False input termination markerprompts/curate_stocks.md:31 · False input termination marker — attempts to end user input sectionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injectionevals/golden/2026-09-13/sources.json:8 · 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
CRITICAL
Prompt injectionevals/golden/2026-09-08/sources.json:8 · 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
Access to sensitive file pathsconfig.py:4 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Hidden zero-width characters detectedevals/golden/2026-09-13/sources.json:5 · Hidden zero-width characters detected — may conceal contentFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
CRITICAL
False input termination markerprompts/curate_us_news.md:48 · False input termination marker — attempts to end user input sectionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
False input termination markerprompts/curate_immigration.md:52 · False input termination marker — attempts to end user input sectionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Authorization escalation languagetoday_knowledge.md:14 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Hidden zero-width characters detectedevals/golden/2026-09-13/sources.json:4 · Hidden zero-width characters detected — may conceal contentFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Hidden zero-width characters detectedevals/golden/2026-09-18/sources.json:5 · Hidden zero-width characters detected — may conceal contentFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Hidden zero-width characters detectedsources/base.py:34 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
CRITICAL
Prompt injectionevals/golden/2026-09-07/sources.json:8 · 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
Hidden zero-width characters detectedevals/golden/2026-09-08/sources.json:5 · Hidden zero-width characters detected — may conceal contentFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
CRITICAL
False input termination markerprompts/curate_ai_news.md:39 · False input termination marker — attempts to end user input sectionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Access to sensitive file pathsDockerfile:11 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsagent/providers/elevenlabs.py:115 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionmain.py:150 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
CRITICAL
Prompt injectionevals/golden/2026-09-18/sources.json:178 · 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
MEDIUM
Process kill commandevals/golden/2026-09-13/sources.json:5 · Process kill command — agent can terminate processesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
File type combined with upload actionevals/golden/2026-09-18/sources.json:5 · File type combined with upload action — agent may exfiltrate local data filesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
CRITICAL
Prompt injectionevals/golden/2026-09-18/sources.json:8 · 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
Hidden zero-width characters detectedevals/golden/2026-09-07/sources.json:5 · Hidden zero-width characters detected — may conceal contentFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Hidden zero-width characters detectedsources/base.py:28 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Access to sensitive file pathsmcp_server.py:30 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

What would make this Verified

20 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim vinay-kumar-godavarti: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Does not do what the description says≈ +5 on the totalIn the sandbox the skill never performed the task it claims (no call to the service it is for). Make sure the happy path runs without extra setup, or describe the real behavior.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Hidden zero-width characters detected≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  6. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim vinay-kumar-godavarti