searching-media
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses authoritative directives to override default agent behavior, such as 'NEVER call search_media_cms_channels, search_electronic_media tools directly' and 'Takes PRIORITY and activates FIRST', which constrains the agent's standard tool selection reasoning.
- [PROMPT_INJECTION]: The skill possesses a potential surface for indirect prompt injection. 1. Ingestion points: Metadata and URLs for media assets are ingested from the
search_media_cms_channelsandsearch_electronic_mediatools as described inSKILL.md. 2. Boundary markers: The instructions lack explicit delimiters to prevent the agent from interpreting instructions that might be embedded in the ingested search results. 3. Capability inventory: The skill has the capability to modify the user's code or components by inserting retrieved URLs as noted inSKILL.md. 4. Sanitization: No specific validation or sanitization of the external tool output is defined before it is applied to the codebase.
Audit Metadata