hookify-rules
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents a rule-based system designed to ingest and process untrusted data from multiple local development sources.
- Ingestion points: The 'Hookify' system, as documented in
SKILL.md, processes bash commands, file paths, file contents (edit/write operations), and user prompts. - Boundary markers: The documentation does not specify the use of boundary markers or delimiters to isolate untrusted content from the rule logic.
- Capability inventory: The system can trigger automated warning messages or block operations (e.g., file writes, bash commands) based on matching patterns in the ingested data.
- Sanitization: No explicit sanitization or validation of the external content is mentioned beyond regex pattern matching.
Audit Metadata