amendment-history
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted documents such as contracts and amendments. These documents serve as an attack surface where malicious instructions could be embedded to influence the agent's behavior during summarization or clause tracking.
- Ingestion points: Reads multiple PDF or text files provided through direct uploads, repository links, or system IDs.
- Boundary markers: The skill does not define explicit delimiters or instructions for the agent to ignore commands that might be found within the ingested contract text.
- Capability inventory: The skill's primary capabilities are text extraction, indexing, and markdown generation. It does not invoke high-risk system commands or network tools.
- Sanitization: There is no evidence of sanitization or filtering of the document content to prevent embedded instructions from affecting the LLM's logic.
Audit Metadata