w-api-docs
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing untrusted content from the local repository. 1. Ingestion points: Instructions direct the agent to read package.json, README.md, and MDX documentation files (SKILL.md). 2. Boundary markers: Absent; there are no delimiters defined to separate file content from the agent's instructions. 3. Capability inventory: The skill permits shell command execution by directing the agent to run generator scripts found in the configuration. 4. Sanitization: Absent; the skill does not perform validation or escaping of the ingested content.
- [COMMAND_EXECUTION]: The skill instructs the agent to identify and run generation commands defined in the repository's package.json. This allows for shell execution based on the local environment's configuration, which could be exploited if the project files are compromised.
Audit Metadata