feedback-analyst

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core purpose of processing untrusted qualitative feedback datasets.
  • Ingestion points: Processes external user-provided feedback corpora, including surveys, support tickets, and reviews, as defined in SKILL.md and meta/skill.json.
  • Boundary markers: The instructions do not define unique delimiters or boundary markers to isolate untrusted input data from the system instructions.
  • Capability inventory: No tools, shell scripts, network access, or file system modifications are requested or used by the skill, which significantly reduces the potential impact of an injection.
  • Sanitization: The skill lacks explicit instructions for sanitizing or filtering input data before interpretation by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 11:46 AM
Security Audit — agent-trust-hub — feedback-analyst