openspec-sync-specs
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the
openspecCLI to list available changes (openspec list --json) and to check the status of a specific change (openspec status --change "<name>" --json). These commands are necessary for the skill to identify which files need to be synchronized. - [EXTERNAL_DOWNLOADS]: The skill documentation specifies a dependency on the
openspecCLI. This is listed as a compatibility requirement in the frontmatter and is a prerequisite for the skill to function, rather than a runtime remote code download. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process the contents of local delta specification files to apply updates to main specs. This ingestion of external file content into the agent's context represents a potential attack surface for indirect prompt injection if those files contain instructions designed to influence agent behavior.
- Ingestion points: Specification files identified in the
artifactPaths.specs.existingOutputPathsmetadata and the main specification files located atopenspec/specs/<capability>/spec.md. - Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious content within the spec files during the merging process.
- Capability inventory: The skill utilizes shell command execution via the CLI and file system read/write capabilities to perform its primary function.
- Sanitization: No specific content sanitization or validation logic is defined; the skill relies on the agent's ability to "intelligently merge" markdown text.
Audit Metadata