openspec-sync-specs
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface where instructions embedded within delta specification files could potentially influence agent behavior.
- Ingestion points: Delta specification files located at openspec/changes//specs/*/spec.md as described in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the delta specs.
- Capability inventory: The agent is granted capabilities to read from and write to the file system to perform the sync.
- Sanitization: There is no explicit sanitization or validation of the content within the delta specs; the agent is instructed to use 'intelligent merging' and 'judgment'.
- [COMMAND_EXECUTION]: The skill uses a local command-line utility to retrieve project metadata.
- Evidence: Execution of 'openspec list --json' to identify available changes in SKILL.md.
Audit Metadata