abaqus-docs
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run a local maintenance script (.claude/skills/abaqus-docs/scripts/download_abqpy_docs.py) using the Bash tool.
- [EXTERNAL_DOWNLOADS]: The skill references external project documentation sources (hailin.wang and github.com/haiiliin/abqpy) for downloading content.
- [INDIRECT_PROMPT_INJECTION]: The skill populates the agent's context with content fetched from external websites, which could host malicious instructions. 1. Ingestion points: Markdown documentation files in .claude/docs/abaqus-api/modules/ updated from external sources. 2. Boundary markers: Absent; there are no delimiters protecting the agent from instructions embedded in the fetched documentation. 3. Capability inventory: The skill has access to Bash execution, file system read, and file system write. 4. Sanitization: Absent; the skill does not specify any verification or sanitization of the documentation content before it is read by the agent.
Audit Metadata