sector-analyst
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided chart images to generate local markdown files, which creates an entry point for indirect prompt injection where malicious instructions could be embedded in the visual data.\n
- Ingestion points: Performance chart images (1-week and 1-month timeframes) provided by the user as described in SKILL.md.\n
- Boundary markers: Absent; the skill does not define specific delimiters or warnings for the agent to ignore potentially embedded instructions in the image data.\n
- Capability inventory: File system write access is utilized to generate analysis reports as specified in the Step 5 workflow of SKILL.md.\n
- Sanitization: Absent; there is no requirement to validate or sanitize the data extracted from the charts before it is interpolated into the final markdown report.
Audit Metadata