monetize
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from external resumes (.docx, .pdf, .md, .txt) or direct text pastes to build a career profile used in strategy generation. Evidence chain: 1. Ingestion points: Résumé files and user-pasted career history in SKILL.md. 2. Boundary markers: Absent; no specific delimiters or ignore-instructions warnings are defined for the parsing of user content. 3. Capability inventory: Writing and reading workspace files (monetize-profile.md, monetization-report.md) and executing a Python linter script. 4. Sanitization: Absent; the skill lacks specific escaping or validation for external content before interpolation.
- [COMMAND_EXECUTION]: The skill invokes a local Python script (scripts/report_lint.py) to validate the structure of the generated monetization report. The script performs deterministic regex-based checks on local file content and does not involve network operations or unsafe system calls.
Audit Metadata