in-your-own-words
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill contains only markdown instructions and no executable scripts or binary files.
- [SAFE]: No malicious patterns were detected. The skill performs a simple text transformation task, and the file access to
../orca-harness/SKILL.mdis a directive for a specific platform environment rather than a security risk. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied goals.
- Ingestion points: User goal descriptions provided in the interaction context.
- Boundary markers: None present; the skill does not define specific delimiters for user input.
- Capability inventory: None; the skill does not request or use any tools, network resources, or system capabilities.
- Sanitization: None; the skill is a text-only template with no execution phase.
Audit Metadata