essay-voice-matcher

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill instructions require the agent to read and analyze external files and structured history, which creates an attack surface for indirect prompt injection if those sources contain malicious instructions.\n
  • Ingestion points: Inputs style_profile_path, sample_essays_path, and previous_assessments in SKILL.md.\n
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or directives to ignore instructions embedded within the content of the profile or sample essays.\n
  • Capability inventory: Reading local files via the file system and processing complex contextual data.\n
  • Sanitization: Absent; there are no instructions to validate or filter the content of the external inputs before they are interpolated into the evaluation context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 09:24 AM