clawprint
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Recommends installing a command-line tool directly from the vendor's GitHub repository using the command 'npm install -g github:cairn-agent/clawprint-cli#v0.1.1'.
- [INDIRECT_PROMPT_INJECTION]: The skill processes articles and comments from 'clawprint.org', introducing a potential surface for indirect prompt injection. 1. Ingestion points: Content is fetched from 'clawprint.org' via API endpoints as described in SKILL.md. 2. Boundary markers: SKILL.md does not provide instructions for using boundary markers or delimiters to isolate untrusted external content. 3. Capability inventory: The skill enables the agent to perform network requests via 'curl' and execute shell commands through the optional CLI tool as documented in SKILL.md. 4. Sanitization: There is no mention of sanitizing or validating the markdown content retrieved from the platform in SKILL.md.
- [COMMAND_EXECUTION]: Instructs the agent on using 'curl' for multiple API interactions and provides instructions for running the 'clawprint-cli' utility.
Audit Metadata