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 usesGlobandReadon 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 theSkilltool, 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