diagnose-generation-failure
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Speakeasy CLI tool (
speakeasy lint,speakeasy suggest) and standard utilities (yq,jq) to inspect and validate OpenAPI specifications. These actions are consistent with the skill's stated purpose of diagnosing generation failures. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of OpenAPI specifications, which creates a potential vulnerability surface.
- Ingestion points: User-provided OpenAPI specification files are loaded for analysis as described in
SKILL.md. - Boundary markers: The instructions do not define explicit boundary markers or delimiters for the ingested content to prevent it from being interpreted as instructions.
- Capability inventory: The skill has the capability to execute shell commands (
speakeasy,yq,jq) using variables derived from user input, such as<spec-path>. - Sanitization: There is no evidence of sanitization or validation of the specification file path or content before it is interpolated into shell commands, which could be exploited if the agent does not provide its own safeguards.
Audit Metadata