openspec-explore
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local codebase and OpenSpec configuration files, which could theoretically contain malicious instructions.
- Ingestion points: Reads project background and conventions from
openspec/config.yaml, existing artifacts fromartifactPaths, and general codebase content during exploration. - Boundary markers: The instructions do not provide explicit delimiters or "ignore embedded instructions" warnings when processing these external file contents.
- Capability inventory: The skill can execute
openspecCLI commands via Bash, read arbitrary files within the project, and write markdown artifacts to specific paths. - Sanitization: No specific sanitization or validation of the ingested file content is described before it is processed by the agent.
Audit Metadata