site-audit
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests raw HTML content from external URLs using webfetch. 1. Ingestion points: webfetch each URL to inspect the raw HTML directly in SKILL.md. 2. Boundary markers: No boundary markers or ignore instructions are specified for the external content. 3. Capability inventory: The skill can execute local Python scripts (scripts/dfs_client.py, scripts/report_publish.py) and write files to the local filesystem. 4. Sanitization: No sanitization or validation of the fetched HTML is described.
- [COMMAND_EXECUTION]: The skill executes local Python scripts to perform auditing and report generation. Evidence: Calls to python scripts/dfs_client.py and python scripts/report_publish.py.
Audit Metadata