skills/udecode/plate/issue-harvester/Gen Agent Trust Hub

issue-harvester

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions suggest installing the gitcrawl utility from an external Homebrew tap (openclaw/tap/gitcrawl).\n- [COMMAND_EXECUTION]: The skill requires the use of several command-line tools to interact with repository data, including gitcrawl, gh (GitHub CLI), ripgrep (rg), and octopool.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: The skill retrieves and reads issue titles, bodies, and comments from GitHub (referenced in SKILL.md and references/gitcrawl.md).\n
  • Boundary markers: The instructions do not define specific delimiters or warnings to prevent the agent from following instructions embedded within the harvested issue data.\n
  • Capability inventory: The agent is authorized to execute multiple CLI tools (gitcrawl, gh, rg, octopool) and write results to the local filesystem in docs/ and .tmp/ directories (referenced in SKILL.md and references/gitcrawl.md).\n
  • Sanitization: No specific sanitization, filtering, or validation of the retrieved GitHub content is described before the agent processes the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 06:54 AM