provider-research-digest

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external reports to author highlights, creating an ingestion surface. 1. Ingestion points: Files located at _reports/reports///<RUN_DATE>.md (SKILL.md). 2. Boundary markers: None identified in instructions. 3. Capability inventory: Uses gh, git, uv run, mktemp, and writes to local files (SKILL.md). 4. Sanitization: No specific sanitization or filtering of the report content is mentioned before processing.
  • [EXTERNAL_DOWNLOADS]: Fetches report data from the vendor's repository pipecat-ai/provider-watch-reports using gh repo clone.
  • [COMMAND_EXECUTION]: Runs local management scripts via uv run python scripts/provider-watch/digest.py and uses standard CLI utilities for file and repository management.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 08:55 PM
Security Audit — agent-trust-hub — provider-research-digest