Skills
skills/nickcrew/claude-ctx-plugin/tool-selection/Gen Agent Trust Hub

tool-selection

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill identifies a surface for indirect prompt injection as it parses user-provided operations to determine tool selection. 1. Ingestion points: The [operation] argument in the /tools:select command (references/select.md). 2. Boundary markers: Absent; no delimiters or ignore-instructions are specified for the operation string. 3. Capability inventory: The reference mentions coordination with execute_sketched_edit and Read/Grep. 4. Sanitization: No sanitization or validation logic for the input string is defined.
  • [NO_CODE] (SAFE): The skill is entirely documentation-based (Markdown) and does not include any scripts, binaries, or automated installation steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:08 PM