spec-planner
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external websites and local files, which creates a surface where malicious instructions embedded in that data could influence the agent's behavior.
- Ingestion points: In Phase 2 (DISCOVER), the skill uses
webfetchto retrieve documentation from the internet andreadto examine local project files. - Boundary markers: The instructions do not define explicit delimiters or 'ignore' directives to prevent the agent from following instructions that might be contained within the retrieved web content or file data.
- Capability inventory: The agent has the capability to write files to the
specs/directory, usesubagentfor delegated tasks, and perform further web searches. - Sanitization: There are no requirements or procedures specified for sanitizing or escaping content retrieved from external sources before it is used in the drafting process.
Audit Metadata