skills/aretedriver/ai-skills/handoff/Gen Agent Trust Hub

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, and git 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, and TODO.md.\n
  • Boundary markers: No specific delimiters are specified for ingested file content.\n
  • Capability inventory: The skill uses Bash, Read, Glob, and Grep tools.\n
  • Sanitization: No content filtering is applied to ingested files, though the skill is instructed to avoid packaging credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 05:16 PM
Security Audit — agent-trust-hub — handoff