loop

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands including git (checkout, add, commit) and python to run experiment evaluation scripts. It also manages persistence via CronCreate and CronDelete calls to schedule recurring tasks.
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface through its autonomous loop.
  • Ingestion points: The agent reads state and configuration from .autoresearch/{domain}/{name}/config.cfg, program.md, and results.tsv as specified in SKILL.md.
  • Boundary markers: There are no delimiters or specific instructions to ignore potential malicious directives within the processed files.
  • Capability inventory: The skill allows the agent to modify files, execute git/python commands, and schedule persistent tasks.
  • Sanitization: No sanitization or verification of the external file content is performed before the agent reviews it to determine future actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 10:00 PM