necromancer
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted content from GitHub issue bodies, creating a surface for indirect prompt injection attacks. \n
- Ingestion points: GitHub issue data retrieved via
gh issue list(SKILL.md). \n - Boundary markers: None identified; untrusted data is processed without delimiters or instructions to ignore embedded commands. \n
- Capability inventory: The skill can modify issue states and post comments using
gh issue editandgh issue comment(SKILL.md). \n - Sanitization: No input validation or sanitization is performed on the ingested issue content.\n- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the repository and issue tracker. \n
- Evidence: Employs
git log,gh pr list, andgh issuecommands to aggregate context and apply changes.
Audit Metadata