job-screening
Warn
Audited by Snyk on Nov 21, 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 job-posting text the user selects and supplies (screenshots, pasted text, PDF/Excel files, or a recruiting URL the agent fetches), which is employer-authored content the agent fetches on demand, not a feed outsiders can post into, so it falls under low.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The README's setup path runs
git cloneagainst an individually owned GitHub repository (Ekko237/job-screening-skill) and then installs its content as the skill, so it is an inbound setup dependency with unofficial provenance pinned only to a tag, giving medium.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The installer copies the skill into the agent's
~/.codexor~/.claudeskill directories, which is an operational change to agent integration. However, its backup-before-overwrite flow, the preservedprofile/, and the lack of--deletemean no irreversible operational loss is established.
Issues (3)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata