antithesis-documentation
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructions advise the agent to retrieve a remote README file (https://raw.githubusercontent.com/antithesishq/snouty/refs/heads/main/README.md) and follow its installation instructions if the user consents. This pattern involves the dynamic execution of instructions retrieved from an external source.\n- [EXTERNAL_DOWNLOADS]: The skill fetches documentation and setup information from vendor-controlled sources including antithesis.com and github.com/antithesishq.\n- [COMMAND_EXECUTION]: The skill uses the snouty CLI to retrieve, search, and display documentation details to the user.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes external documentation content, which could potentially influence agent behavior if the source content were manipulated.\n
- Ingestion points: Documentation fetched from https://antithesis.com/docs/ and output from snouty docs commands.\n
- Boundary markers: None identified.\n
- Capability inventory: Shell command execution via the snouty CLI and network access for document retrieval.\n
- Sanitization: No specific validation or sanitization of the retrieved markdown content is performed before processing.
Audit Metadata