skill-strategy-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes data from potentially untrusted sources.\n
- Ingestion points: The skill accepts and processes user-provided content data in formats such as CSV, screenshots, and text (SKILL.md, Step 1).\n
- Boundary markers: The instructions lack explicit markers or warnings to isolate processed data from the agent's core instructions.\n
- Capability inventory: The skill performs file read operations on configuration files (identity.md, platforms.md, audience.md, preferences.md) and file write operations to the 'outputs/' directory.\n
- Sanitization: No data sanitization or validation steps are included in the processing pipeline.
Audit Metadata