openspec-sync-specs
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
openspec list --jsoncommand to retrieve information about available changes. This command execution is part of the primary functionality provided by the skill author. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external requirement specification files which may contain instructions that influence agent behavior.
- Ingestion points: Delta spec files at
openspec/changes/<name>/specs/*/spec.mdand main spec files atopenspec/specs/<capability>/spec.md(identified in SKILL.md). - Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between the specification content and potential instructions to the agent.
- Capability inventory: The skill possesses the capability to modify and create files on the local filesystem, specifically targeting the
openspec/specs/directory. - Sanitization: No sanitization or validation of the content read from the Markdown files is mentioned before the agent uses that content to perform file edits.
Audit Metadata