openspec-sync-specs
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
openspec list --jsoncommand. This is a vendor-specific CLI tool used to retrieve metadata required for the synchronization process. This is a standard operation within the intended use-case of the skill. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes data from external specification files to determine how to edit other files.
- Ingestion points: Reads delta specification content from files located at
openspec/changes/<name>/specs/*/spec.md. - Boundary markers: Absent; the agent is instructed to interpret Markdown headers (e.g.,
## ADDED Requirements) without explicit delimiters or warnings to ignore instructions within those sections. - Capability inventory: The skill has the capability to read from and write to the local filesystem (specifically
.mdfiles in theopenspec/directory) and execute theopenspecCLI. - Sanitization: No sanitization is performed on the input file content before it is processed by the agent; the skill relies on the user to select the appropriate 'change' to sync.
Audit Metadata