setup-issue-tracker
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and analyzes existing repository files (e.g.,
AGENTS.md,CLAUDE.md,GLOSSARY.md) and Git metadata to determine the current project state. If these files contain adversarial instructions, they could potentially influence the skill's recommendations.\n - Ingestion points:
AGENTS.md,CLAUDE.md,GLOSSARY.md,GLOSSARY-MAP.md, and.git/configat the repository root.\n - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when reading these files.\n
- Capability inventory: The skill can execute
git remote -v, write multiple markdown files to thedocs/agents/directory, and update the repository's agent instruction files.\n - Sanitization: No specific sanitization or filtering of the ingested content is documented.\n- [COMMAND_EXECUTION]: The skill facilitates the use of command-line tools like
git,gh(GitHub), andglab(GitLab) for repository analysis and issue tracker interaction. The commands used are standard for these tools and are documented as templates for future agent interactions.
Audit Metadata