audit-skill-by-derailment

Warn

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch content from arbitrary GitHub repositories using gh api. These files are downloaded to a temporary directory (/tmp/skill-test/) and subsequently used as primary instructions for a subagent.
  • [PROMPT_INJECTION]: The skill is highly vulnerable to Indirect Prompt Injection (Category 8). It downloads untrusted SKILL.md and reference files from remote repositories and directs a subagent to follow their instructions.
  • Ingestion points: SKILL.md Step 1 downloads remote skill files via the GitHub API.
  • Boundary markers: Absent. The subagent prompt in Step 3 does not use delimiters or sanitization for the untrusted remote content.
  • Capability inventory: The subagent follows the downloaded skill's workflow, which may include file reads, writes, and network operations across multiple scripts (e.g., scripts/launch-derailment.sh).
  • Sanitization: No validation or filtering is applied to the downloaded content before it is processed by the subagent.
  • [COMMAND_EXECUTION]: The script scripts/launch-derailment.sh uses bash -lc "$agent_cmd" to execute a shell command provided by the user or environment. While intended for agent CLI integration, this pattern provides a direct path for arbitrary command execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 17, 2026, 10:40 PM
Security Audit — agent-trust-hub — audit-skill-by-derailment