readthedocs-redirects-manager
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
curlto perform API requests toapp.readthedocs.organdapp.readthedocs.com. These operations are limited to the official Read the Docs service domains and are necessary for the skill's primary function of managing documentation redirects. - [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting and processing data from an external API, which could be manipulated to contain malicious instructions.
- Ingestion points: Redirect fields, including source paths and descriptions, are retrieved via the
GET /api/v3/projects/{slug}/redirects/endpoint inSKILL.md. - Boundary markers: The skill does not define explicit delimiters or instructions to the agent to disregard potential commands embedded within the retrieved data.
- Capability inventory: The agent has the capability to create, update, and delete project redirects via
POST,PUT, andDELETErequests. - Sanitization: There is no documented logic for the agent to sanitize or validate the content of the API responses before acting on them.
Audit Metadata