contact-cache
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external CSV files and command-line arguments, creating a surface for indirect prompt injection if the stored data contains malicious instructions intended for the agent.
- Ingestion points: The
scripts/cache.pyscript ingests data from external files provided via the--csvargument and user-supplied strings via--notes,--name, and--strategyarguments. - Boundary markers: No boundary markers or 'ignore' instructions are used to wrap the imported data before it is stored or exported.
- Capability inventory: The skill possesses file-write capabilities (writing to
skills/contact-cache/data/contacts.csv) and command execution capabilities (via the agent running the Python script). - Sanitization: The script performs data normalization for ID generation (SHA256 hashing) but does not sanitize the actual content of the fields (names, notes, etc.) to strip potential instructions or control characters.
Audit Metadata