recall

Pass

Audited by Gen Agent Trust Hub on Nov 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/history.py executes git commands using the subprocess module to resolve repository metadata.
  • Evidence: It uses subprocess.run to call commands like git worktree list and git rev-parse on the target repository path.
  • Security Note: These calls are implemented using argument lists rather than shell strings, which is a secure practice that prevents shell-based command injection.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from previous chat sessions and shared records, which is a known attack surface for indirect prompt injection.
  • Ingestion Points: Historical transcript data is read from local directories (~/.codex, ~/.claude) and external sources (issue trackers, PRs) via the agent's MCP tools.
  • Boundary Markers: The skill documentation in references/history.md explicitly states that history output is marked as untrustedEvidence to alert the agent to potential risks.
  • Capability Inventory: The skill utilizes the git and gh command-line tools and has the ability to spawn subagents using the /swarm role.
  • Sanitization: The SKILL.md instructions include a mandatory step to sanitize private context before any public output is generated.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 17, 2026, 09:11 AM