experiment-code

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess.run to execute Python scripts (experiment.py, plot.py) that it generates or modifies at runtime, as defined in the execution loops in references/code-patterns.md.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it incorporates untrusted data into code that is subsequently executed.
  • Ingestion points: Research plans, ideas, and error logs provided via the $1 input variable in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its own logic and potentially malicious instructions embedded within user-supplied ideas or logs.
  • Capability inventory: The skill can write and read files in the project directory and execute shell commands via subprocess.run.
  • Sanitization: No sanitization or code verification is performed on the generated scripts before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 07:28 AM