technical-writing
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes, reviews, and improves user-provided technical documentation. This creates a surface where malicious instructions could be embedded in the documentation content to influence the agent's behavior.
- Ingestion points: Technical documentation files (READMEs, API specs, tutorials, etc.) provided by the user for processing as described in SKILL.md.
- Boundary markers: The instructions lack explicit delimiters or safety prompts to isolate untrusted user-provided content from the agent's core instructions.
- Capability inventory: The skill is designed for use in environments that typically allow file system access and shell command execution, which could be abused if an injection is successful.
- Sanitization: No explicit sanitization or filtering of control sequences within the ingested documentation is defined.
- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of companion skills from an external GitHub repository using the npx package runner, which executes code from the source.
- Evidence: The skill documentation refers to the AbsolutelySkilled GitHub organization and provides the command 'npx skills add AbsolutelySkilled/AbsolutelySkilled --skill ' for adding related tools.
Audit Metadata