tech-logos
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that involves ingesting external data from registries and proposed files, which represents a potential surface for indirect prompt injection if those assets contain malicious instructions.
- Ingestion points: logo index, proposed files, and external registries (e.g., Elements).
- Boundary markers: None explicitly defined in the instructions to prevent the agent from following instructions embedded within logo metadata or SVG code.
- Capability inventory: The agent is instructed to write files to the shared logo directory and update public exports.
- Sanitization: No specific sanitization or validation procedures are mentioned for the external assets.
- [NO_CODE]: The skill consists exclusively of markdown instructions and does not include any scripts, binaries, or other executable code.
Audit Metadata