plain-english
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external documents (contracts) as its primary input, creating an attack surface for indirect prompt injection. Malicious instructions hidden within a contract could attempt to influence the agent's summary or behavior.
- Ingestion points: Instructions in
SKILL.md(Step 1) require the agent to read the full contract from a user-provided file path or pasted text. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers for the processed text.
- Capability inventory: The skill uses
Read,Glob, andGreptools (as defined in the frontmatter) to access the file system and generates a new markdown file as output. - Sanitization: The skill does not implement validation or filtering to distinguish between contract text and potential embedded commands.
Audit Metadata