openspec-sync-specs
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from delta specification files located at
openspec/changes/<name>/specs/*/spec.mdto update main specification files. This untrusted content is interpreted by the agent to perform "intelligent merging," which lacks explicit boundary markers or sanitization to prevent the agent from potentially following instructions embedded within the data. - Ingestion points: Delta specification files found at
openspec/changes/<name>/specs/*/spec.md. - Boundary markers: Absent; the agent is instructed to read markdown sections and apply changes based on their content.
- Capability inventory: The skill performs file read and write operations on main specification files and executes the
openspecCLI tool via subprocess. - Sanitization: Absent; the skill relies on the agent's judgment to merge changes sensibly without pre-processing the input for malicious instructions.
- [COMMAND_EXECUTION]: The skill executes the
openspec list --jsoncommand to retrieve a list of available changes. This is a functional requirement for the skill's specification management workflow.
Audit Metadata