openspec-sync-specs
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
openspecCLI tool with thelist --jsoncommand to retrieve available changes from the local environment. - [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection (Category 8) because it reads content from external files and uses that content to determine how to modify other project files.
- Ingestion points: The agent reads delta specification files located at
openspec/changes/<name>/specs/*/spec.mdas described in Step 2 and Step 3a. - Boundary markers: None. The skill does not instruct the agent to use delimiters or ignore instructions embedded within the delta specs.
- Capability inventory: The agent is authorized to create and modify specification files at
openspec/specs/<capability>/spec.mdusing the logic defined in Step 3c and 3d. - Sanitization: There is no evidence of sanitization or validation of the input content before it is used to perform 'intelligent merging' into the main specification files.
Audit Metadata