fallow-review

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPERSISTENCECOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a persistent file-monitoring pipeline that automatically ingests content from a local file (.fallow-review/feed.jsonl) and injects it into the agent's active prompt context.\n
  • Ingestion points: The hooks/fallow-review-on-feedback.sh script is triggered on file changes to read new lines from the review feed.\n
  • Boundary markers: The script wraps the injected content with a warning stating that the feedback consists of unverified human notes to be weighed as input, which serves as a weak instructional boundary.\n
  • Capability inventory: The skill allows the agent to read repository files, execute git operations, and write structured review data to JSON files on disk.\n
  • Sanitization: The ingestion script extracts the note field using jq but does not perform sanitization or filtering of the string content to remove potential prompt injection markers before context injection.\n- [PERSISTENCE]: The skill relies on registering SessionStart and FileChanged hooks in the platform configuration (.claude/settings.json), causing the monitoring scripts to be executed automatically whenever the session starts or relevant files are modified.\n- [COMMAND_EXECUTION]: The skill executes local shell scripts (hooks/fallow-review-session-init.sh and hooks/fallow-review-on-feedback.sh) to manage the feedback loop and update the agent's context dynamically.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 10:07 AM
Security Audit — agent-trust-hub — fallow-review