Skills
skills/jeremylongshore/claude-code-plugins-plus/agent-context-loader/Gen Agent Trust Hub

agent-context-loader

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill's primary function is to discover and merge external instructions, which creates a surface for indirect prompt injection.
  • Ingestion points: The skill instructions in SKILL.md direct the agent to scan and read AGENTS.md files from the current directory and its ancestor directories.
  • Boundary markers: Absent. There are no instructions provided to the agent to use delimiters or ignore embedded directives when processing the discovered files.
  • Capability inventory: The skill is configured with powerful tools including Write, Edit, and Bash (as defined in SKILL.md allowed-tools), and scripts/check-agents-md.sh performs filesystem existence checks.
  • Sanitization: Absent. The instructions specify a direct merge of discovered contexts without any validation or filtering of the external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 01:54 PM