document-ai-hero-api
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to perform local file system read and write operations to document an existing project. This behavior aligns with its stated purpose and the author context provided. The skill requires specific read permissions for the repository path, which is a security best practice for local environment access.\n- [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill instructs the agent to read and process external source code files which could theoretically contain malicious instructions. However, the associated risk is low because the agent is not granted high-privilege capabilities such as network access or shell execution during this process.\n
- Ingestion points: Local source code files within
~/repos/ai/course-builder/apps/ai-hero/src/(referenced in SKILL.md).\n - Boundary markers: None explicitly defined in the file scanning instructions to prevent the agent from following instructions embedded within the source code.\n
- Capability inventory: Local file read and write operations; no network access or dynamic code execution capabilities are utilized.\n
- Sanitization: No specific content validation, escaping, or filtering of the ingested source code is described in the workflow.
Audit Metadata