growth-ceo

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted data from the local codebase as its primary source of context.\n
  • Ingestion points: The skill explicitly reads the codebase, README, and documentation in SKILL.md (Phase 1 and Step 1 of the Workflow) to understand the product territory.\n
  • Boundary markers: There are no instructions in the skill to use delimiters or ignore instructions embedded within the analyzed project files.\n
  • Capability inventory: The skill has access to Read, Write, Edit, Glob, and Grep tools, which could be leveraged to modify the filesystem if the model is influenced by malicious instructions in the input data.\n
  • Sanitization: No content sanitization or validation mechanisms are implemented to filter instructions from the ingested codebase content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 11:40 PM