prompt-master

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to its core function of processing untrusted inputs.\n
  • Ingestion points: Untrusted data enters the agent context through the 'Skill Scan' phase in SKILL.md, which uses Glob and Read on other installed skills, and the 'Discovery' phase, which accepts task descriptions and prompts from users.\n
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested text during the analysis phases.\n
  • Capability inventory: The skill is authorized to use Read, Glob, Grep, AskUserQuestion, and the Skill tool, the latter of which can be used to invoke other agents based on the analyzed input.\n
  • Sanitization: No explicit sanitization or validation of the content retrieved from local files or user input is described in the logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 07:53 AM