consult-the-library
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it reads and processes content from external repositories stored locally.
- Ingestion points: Files within the .library/ directory as specified in SKILL.md.
- Boundary markers: Absent; the instructions do not define delimiters or provide the agent with guidance to ignore embedded instructions in the reference material.
- Capability inventory: The workflow involves file system searching and reading using tools like rg (ripgrep) and standard file reads.
- Sanitization: No sanitization or verification of the external content is performed before it is presented to the agent.
Audit Metadata