dependency-doctor
Warn
Audited by Snyk on Nov 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow reads only the user's own manifest offline, and only with user-approved
--onlinedoes it fetch PyPI release metadata, where the maintainer-authoredyanked_reasontext is copied into the finding and read by the agent, so this is low risk because the agent must actively fetch that outsider-published metadata for a specific pinned release.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The only inbound source is the README's setup command that fetches the skill from a GitHub repository under Shubhamsaboo, an individual-owned repository rather than a first-party publisher, so it is common/reputable unofficial and rates medium; the PyPI yank lookup is outbound metadata used only for reporting and does not count.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata