handoff
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns such as obfuscation, exfiltration, or persistence were detected. The skill's behavior aligns with its stated purpose of project state documentation.\n- [COMMAND_EXECUTION]: The skill uses the Bash tool to run non-administrative git commands for context gathering.\n
- Evidence: Documentation identifies usage of
git status,git log,git branch, andgit diff --stat.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests untrusted data from the repository environment.\n - Ingestion points: Git commit history,
.claude/plans/files,CLAUDE.md, andTODO.md.\n - Boundary markers: No specific delimiters are specified for ingested file content.\n
- Capability inventory: The skill uses
Bash,Read,Glob, andGreptools.\n - Sanitization: No content filtering is applied to ingested files, though the skill is instructed to avoid packaging credentials.
Audit Metadata