openspec-sync-specs
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads delta spec files from the filesystem (
openspec/changes/<name>/specs/*/spec.md) and uses the content to modify or create main spec files. This ingestion of external data without explicit sanitization or boundary markers could allow malicious instructions embedded in a spec file to influence the agent's behavior during the sync process. - Ingestion points: Delta spec files located at
openspec/changes/<name>/specs/*/spec.md. - Boundary markers: None defined; the agent is instructed to read the text and apply changes based on markdown headers.
- Capability inventory:
openspec listcommand execution, file reading, and file writing to theopenspec/specs/directory. - Sanitization: No explicit sanitization or validation of the input file content is mentioned.
- [COMMAND_EXECUTION]: The skill executes the
openspec list --jsoncommand to retrieve available changes. This is a functional requirement of the skill to facilitate user selection and does not involve user-provided arguments in a dangerous way.
Audit Metadata