ad-campaign-analyzer
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill contains no executable code, remote script downloads, or network exfiltration patterns. It operates purely as a template for processing user-provided data via AI reasoning.
- [NO_CODE]: There are no scripts, binaries, or automated workflows included with this skill. It relies entirely on the agent's ability to follow the markdown instructions provided in SKILL.md.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes untrusted data (CSV exports and pasted tables) without explicit boundary markers. However, given the purely analytical nature and lack of dangerous tools, this is considered a low-risk surface.
- Ingestion points: Campaign data intake (CSV, pasted tables, screenshots) in SKILL.md.
- Boundary markers: None identified in the prompt to separate user data from instructions.
- Capability inventory: Local file system write (saving reports to the 'clients/' directory).
- Sanitization: None specified for the input data.
Audit Metadata