speech-recognition
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as an instructional guide that processes user queries to provide coding assistance and architectural reviews.
- Ingestion points: User prompts requesting code snippets or implementation reviews, as illustrated in the
evals/evals.jsonfile. - Boundary markers: The documentation uses standard Markdown headers and triple-backtick code blocks to separate descriptive text from Swift implementation examples.
- Capability inventory: The skill is composed of static Markdown and JSON metadata; it does not include any scripts, executables, or tool definitions that would grant the agent the ability to perform file system operations, execute shell commands, or make network requests.
- Sanitization: As an informational resource, the skill provides templates and best practices rather than implementing runtime input filtering.
Audit Metadata