match
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted job description text that could contain hidden instructions to manipulate the analysis or exfiltrate resume data.
- Ingestion points: External job description text or file paths provided as arguments in Step 1.
- Boundary markers: None identified; there are no delimiters or specific instructions to the agent to isolate the job description content from its operational instructions.
- Capability inventory: The skill has access to read local files (resume.yaml, skills.yaml) and write/append to files in the knowledge/sessions/ directory.
- Sanitization: No validation or sanitization is performed on the job description text or the slugs used to construct file paths for session logging.
Audit Metadata