Skills
Navigate
skills/fortunto2/solo-factory/solo-github-outreach/Gen Agent Trust Hub

solo-github-outreach

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external GitHub repositories to generate outreach drafts.
  • Ingestion points: Repository README and manifest files are fetched in scripts/evaluate.py.
  • Boundary markers: No delimiters or warnings are used to isolate external content from instructions.
  • Capability inventory: The skill utilizes Bash, Write, and Edit tools to process data and generate files.
  • Sanitization: No filtering or validation is applied to retrieved repository content before it is presented to the agent.
  • [COMMAND_EXECUTION]: Instructions in SKILL.md suggest executing shell commands on content from external repositories.
  • Evidence: The manual evaluation steps include performing a shallow git clone and running grep on third-party source code.
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations to fetch data from GitHub repositories.
  • Evidence: scripts/enrich.py and scripts/evaluate.py use the gh tool to communicate with the GitHub API and retrieve file contents.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 11:41 AM