bq-skill

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content, including job descriptions and user-supplied resumes, which could contain adversarial instructions intended to influence the agent's behavior.
  • Ingestion points: External job description text and candidate resumes are ingested into the agent context in prompts/jd-driven-prep.md (Step 1 and Step 2).
  • Boundary markers: The skill does not explicitly utilize delimiters or instructions to ignore potential commands embedded within the ingested external documents.
  • Capability inventory: The skill performs file-write operations, specifically creating and saving HTML reports to a specific path on the user's desktop as instructed in prompts/jd-driven-prep.md (Step 7).
  • Sanitization: There are no documented filtering or sanitization steps applied to the ingested external content before it is used to generate preparation templates and reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 04:24 PM
Security Audit — agent-trust-hub — bq-skill