Freelance
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external documents like contracts, invoices, and portal exports provided by the user.
- Ingestion points: Pasted contract and invoice data as described in the body of
SKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potentially malicious embedded commands in the processed external data.
- Capability inventory: The skill performs file read, write, and move operations within localized directories including
~/Clawic/data/,~/freelance/, and~/clawic/freelance/. - Sanitization: Instructions are included to identify and scrub credentials and secrets (e.g., API keys, tokens, identifiers) from the ingested text, replacing them with sanitized pointers.
Audit Metadata