skill-creator-flagos

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface. The skill reads and analyzes existing SKILL.md files and associated resources in Mode 2 (Improve) and Mode 3 (Validate). These files are treated as data, which could contain malicious instructions designed to influence the agent's behavior during the improvement or validation process.\n
  • Ingestion points: SKILL.md and supporting files in the skills/ directory.\n
  • Boundary markers: None observed in the instructions for reading/analyzing files.\n
  • Capability inventory: Filesystem access (Read, Write, Edit), shell command execution (Bash), and agent invocation (Agent).\n
  • Sanitization: No explicit sanitization or validation of the content of the analyzed files is described.\n- [COMMAND_EXECUTION]: The skill performs filesystem operations and executes Python scripts using Bash. Specifically, it uses chmod +x to ensure scripts it creates or validates are executable. While chmod can be used for privilege escalation, its use here is restricted to the skill's own directory structure and is a standard requirement for developer tooling.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 03:33 AM