openspec-sync-specs
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes 'delta spec' markdown files, which are untrusted external inputs that could contain malicious instructions designed to influence the agent's behavior during the sync process.
- Ingestion points: The agent reads delta spec files identified through the
existingOutputPathsfield in the output ofopenspec statusas defined inSKILL.md. - Boundary markers: Absent. The instructions do not include specific delimiters or directives to the agent to ignore or isolate instructions that might be embedded within the requirement descriptions or scenarios in the delta specs.
- Capability inventory: The skill allows the agent to execute
openspecCLI commands via Bash and perform file system writes to modify main specification files (spec.md). - Sanitization: Absent. The skill performs a semantic merge of text content from the delta specs into the main specs without validating or sanitizing the content for potential injection attacks.
Audit Metadata