clawd-docs-v2
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches documentation updates from the official vendor domain at https://docs.clawd.bot/ using a core fetch utility.
- [COMMAND_EXECUTION]: Uses standard shell commands including 'ls', 'cat', 'grep', and 'head' to manage and read local documentation data in '~/clawd/data/'.
- [PROMPT_INJECTION]: Indirect Prompt Injection surface analysis:
- Ingestion points: Documentation text is ingested from 'https://docs.clawd.bot/' and local files in '~/clawd/data/docs-snippets/'.
- Boundary markers: None identified; fetched content is processed as standard markdown.
- Capability inventory: The skill has access to local file system commands ('ls', 'cat', 'grep', 'head') and network retrieval ('web_fetch').
- Sanitization: No specific sanitization or schema validation is performed on the documentation content before it is read by the agent.
Audit Metadata