simplify-documents
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a bundled Python script (
scripts/audit_simplification.py) to verify the fidelity and compression ratio of the processed document. The script uses standard libraries and performs analysis on local files passed as arguments. - [INDIRECT_PROMPT_INJECTION]: Because the skill processes and rewrites content from external documents, there is a risk that instructions embedded within those documents could influence the agent's behavior during the simplification process.
- Ingestion points: The skill ingests raw document text or extracted file content provided by the user.
- Boundary markers: The instructions rely on natural language directives to preserve facts and constraints, without specific technical delimiters for input data.
- Capability inventory: The skill utilizes file reading and local script execution for auditing purposes.
- Sanitization: Input documents are processed as-is without sanitization or filtering of embedded instructions.
Audit Metadata