readthedocs-project-manager
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted project data which is interpolated into shell command templates.\n
- Ingestion points: Project
name,slug, andrepository.urlparameters defined in SKILL.md.\n - Boundary markers: Absent; no delimiters or explicit instructions are provided to separate data from command structure.\n
- Capability inventory: Shell command execution via
curlis used for all project management tasks in SKILL.md.\n - Sanitization: No sanitization or validation of these input fields is performed before they are placed into command strings.\n- [COMMAND_EXECUTION]: The skill provides templates for executing
curlcommands in a shell environment, which involves variable interpolation of user-controlled project information.
Audit Metadata