Skills
skills/autumnsgrove/groveengine/gathering-planning/Gen Agent Trust Hub

gathering-planning

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection (Category 8). 1. Ingestion points: Untrusted data enters the context via the 'brain dump' user input and by scanning the codebase for TODO/FIXME comments using the gf tool. 2. Boundary markers: There are no delimiters or specific system instructions used to separate the ingested data from the agent's core instructions. 3. Capability inventory: The skill utilizes gf for file reading and gw gh issue batch for writing data to an external service (GitHub). 4. Sanitization: No sanitization or validation is applied to the content extracted from the codebase or the user's ideas before they are processed and published as GitHub issues.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 04:16 AM