sales-narrative

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONINGNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided text, such as product descriptions and pitch deck outlines. This creates a surface where an attacker could embed malicious instructions in the input data to manipulate the agent's behavior during the review process.
  • [METADATA_POISONING]: The 'What This Skill Cannot Do' section includes irrelevant restrictions about 'audio engineering expertise' and 'audio files', which is a clear mismatch with the skill's purpose as a sales narrative tool. This suggests a template copy-paste error.
  • [SAFE]: No command execution, remote script downloads, or data exfiltration patterns were detected in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:26 PM