rss-feed-discovery
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using vendor-specific CLI tools like
subscription-researchanddigestpilot-runtime. It also encourages running local scripts such asscripts/doctor.mjsandscripts/bootstrap-runtime.mjsfor environment setup. - [PROMPT_INJECTION]: The skill processes untrusted data from external web pages via the
--urlflag and local files via the--inputflag, creating a surface for indirect prompt injection. - Ingestion points: External URLs provided at runtime and local text/markdown files in the repository.
- Boundary markers: Absent. There are no instructions to wrap or delimit input data to prevent it from being interpreted as agent commands.
- Capability inventory: The skill utilizes network access to fetch feeds and file system access to read inputs and write patches/registries.
- Sanitization: Absent. The instructions do not define validation or sanitization steps for the discovered feed metadata before it is incorporated into registry patches or output summaries.
Audit Metadata