skill-forge-eval

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external skill descriptions and user-defined evaluation sets to drive its multi-agent workflow, creating a surface for indirect prompt injection. \n
  • Ingestion points: Ingests natural language instructions from external SKILL.md files during auto-generation (Step 1b) and from evals/evals.json or user-specified files (Step 1). \n
  • Boundary markers: The prompt templates for sub-agents lack explicit delimiters or instructions to ignore potential commands embedded within the evaluated content. \n
  • Capability inventory: The skill spawns sub-agents (executor, grader, analyzer), executes local Python scripts, and performs extensive filesystem write operations. \n
  • Sanitization: There is no evidence of sanitization, escaping, or validation for the content ingested from external skills or user prompts. \n- [COMMAND_EXECUTION]: The skill automates core functionality by invoking local Python scripts. \n
  • Evidence: Uses subprocess calls to execute scripts/generate_eval_set.py for bootstrapping test sets and scripts/aggregate_benchmark.py for data processing. These scripts are internal to the skill's package.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 04:45 PM