afa-sms
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and reference files. No executable scripts, binary files, or network operations were detected.
- [SAFE]: Analysis for prompt injection, obfuscation, and data exfiltration found no malicious patterns. The instructions prioritize compliance with SMS regulations such as TCPA and GDPR.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external brand data from sources like products.md and learnings.jsonl. Ingestion points: products.md, voice-and-tone.md, audience.md, learnings.jsonl. Boundary markers: Absent. Capability inventory: None. Sanitization: Absent. The analysis confirms an ingestion surface exists but determines it is not exploitable due to the absence of sensitive system capabilities.
- [SAFE]: All external references are to internal project files or standard marketing concepts. No suspicious third-party URLs or unverified dependencies were detected.
Audit Metadata