update-issue-tree
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious prompt injection patterns or attempts to override agent safety protocols were found in the SKILL.md instructions.\n- [SAFE]: The skill's network operations are restricted to interactions with the GitHub API for issue management, consistent with its primary purpose. No sensitive data exfiltration or hardcoded credentials were detected.\n- [SAFE]: No obfuscation methods, such as hidden Unicode characters or encoded commands, are present in the skill files.\n- [SAFE]: The skill executes local scripts provided within the package rather than fetching remote code at runtime. It relies on the standard GitHub CLI (gh) tool.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external content from GitHub issues. It implements robust sanitization in
update-root-body.sh, neutralizing potential injection vectors in issue titles and labels using HTML entity encoding and character escaping. It also uses explicit boundary markers (<!-- update-issue-tree:... -->) to protect the integrity of the root issue body. (Severity: SAFE)
Audit Metadata