stophy-parse
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from file formats such as PDF, Word, Excel, and PowerPoint, which can contain hidden instructions designed to manipulate the agent's logic.
- Ingestion points: Local files provided via base64 encoding and remote files accessed via URLs.
- Boundary markers: No delimiters or warnings are specified to help the agent distinguish between document content and its own instructions.
- Capability inventory: The skill utilizes Bash command execution through the Stophy CLI.
- Sanitization: No sanitization or validation of the parsed content is mentioned in the instructions.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute shell commands using the 'stophy' and 'npx' tools to perform parsing and scraping tasks.
Audit Metadata