manage-openapi-overlays

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external OpenAPI specifications and overlay files which are treated as untrusted data.
  • Ingestion points: The skill accepts 'Target spec' and 'Overlay file' as primary inputs for its operations (SKILL.md).
  • Boundary markers: There are no specific instructions to the agent to treat the content of these files as data only or to ignore instructions embedded within them.
  • Capability inventory: The agent is instructed to execute filesystem and network-capable commands via the 'speakeasy' CLI, such as 'overlay apply', 'lint', and 'run' (SKILL.md, content/validation.md).
  • Sanitization: The instructions do not specify any validation or sanitization steps for the contents of the specs or overlays before they are passed to the CLI tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:45 PM
Security Audit — agent-trust-hub — manage-openapi-overlays