gh-issue-workflow
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a controlled workflow that separates read-only investigation from write operations, minimizing the risk of accidental repository changes.
- [SAFE]: Explicit instructions require the agent to obtain human authorization before performing any remote mutation on GitHub issues.
- [NO_CODE]: The skill consists exclusively of instructional text and templates; no scripts, binaries, or external dependencies are present.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and process data from external GitHub issues and repositories.
- Ingestion points:
SKILL.md(INVESTIGATE mode reads repository and issue state). - Boundary markers: No explicit delimiters or isolation instructions for external content are provided.
- Capability inventory:
SKILL.md(WRITE and IMPLEMENT modes enable GitHub mutation and code modification). - Sanitization: No data sanitization procedures are specified.
- Mitigation: The risk of automated exploitation is mitigated by the mandatory human-in-the-loop authorization required for all external actions.
Audit Metadata