planning-with-files

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from planning files and session history which is then injected into the model's prompt.
  • Ingestion points: Reads content from task_plan.md, findings.md, progress.md, and local agent session records (transcripts) stored in Claude Code, Codex, and OpenCode directories.
  • Boundary markers: Uses ===BEGIN-PWF-DATA=== and ===END-PWF-DATA=== delimiters. v3 modes introduce per-session nonces to prevent delimiter-confusion attacks.
  • Capability inventory: The skill operates within an environment where Bash, Write, Edit, Read, Glob, and Grep tools are available.
  • Sanitization: Implements hash attestation (via attest-plan.sh) to verify that the plan has been approved before injection. The inject-plan.sh script explicitly labels injected content as untrusted data and uses nonces to raise the bar against adversarial content.
  • [COMMAND_EXECUTION]: The skill utilizes several local shell and Python scripts (skill-hook.sh, inject-plan.sh, session-catchup.py, etc.) to manage plan lifecycle events and context injection. These scripts perform necessary filesystem operations, path normalization, and integrity checks as part of the skill's intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 09:48 PM
Security Audit — agent-trust-hub — planning-with-files