ctf-orchestrator
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to triage untrusted CTF challenge files. However, this is an inherent and necessary part of the skill's primary function. Ingestion points: Challenge files and directories read during triage (SKILL.md). Boundary markers: None specified. Capability inventory: Execution of local triage tools (strings, file, checksec, exiftool, binwalk, xxd) and script generation/execution. Sanitization: Not specified.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute standard command-line tools and generate scripts to automate repetitive tasks. This behavior is consistent with the skill's purpose and is performed within the local challenge environment.
Audit Metadata