sec-plain-english
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a set of natural language instructions for text rewriting and auditing. No executable code, shell commands, or network operations are present. All external references target official U.S. Government domains (sec.gov) for attribution and source verification.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-supplied financial disclosures for rewriting.
- Ingestion points: Input text provided by the user to the agent for rewriting in plain English.
- Boundary markers: The instructions do not define explicit delimiters for input data.
- Capability inventory: No capabilities for file system modification, network communication, or system command execution are defined or requested in the skill files.
- Sanitization: None; however, the risk is neutralized by the complete absence of exploitable capabilities within the skill's scope.
Audit Metadata