alt-text
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes user-provided images and text descriptions, which could potentially contain instructions to override the agent's behavior or safety guidelines.
- Ingestion points: User-attached images and the 'post or blogpost' context referenced in the task instructions within SKILL.md.
- Boundary markers: Absent; user content is interpolated directly into the prompt without delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill has no execution capabilities (no tool usage, network calls, or filesystem access), minimizing the impact of a successful injection to the generated text output.
- Sanitization: No validation or sanitization of external input is specified.
- [NO_CODE]: This skill consists solely of instructions and metadata, containing no scripts, dependencies, or executable files.
Audit Metadata