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 is designed to read and investigate the local codebase and project configuration files (such as 'openspec/config.yaml'), which introduces a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The skill reads local codebase files, integration points, and project-specific configuration files (SKILL.md).
- Boundary markers: There are no instructions providing specific delimiters or warnings to the agent to disregard instructions found within the files it reads.
- Capability inventory: The skill has access to the 'openspec' CLI tool via Bash, allowing it to create change proposals, designs, and other project artifacts (SKILL.md).
- Sanitization: No sanitization or validation steps are described for the content retrieved from the local environment before it is processed by the agent.
Audit Metadata