skills/udecode/plate/ce-compound/Gen Agent Trust Hub

ce-compound

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it ingests and processes untrusted data from conversation history and investigation steps to generate documentation.
  • Ingestion points: Conversation history and historical investigation steps analyzed by parallel subagents in Phase 1 (SKILL.md).
  • Boundary markers: Not explicitly defined in the instructions for subagents to distinguish between legitimate conversation and potential embedded instructions (SKILL.md).
  • Capability inventory: The skill has the ability to write files and create directories within the docs/solutions/ project path (SKILL.md).
  • Sanitization: The skill validates YAML frontmatter against a schema but does not specify sanitization or escaping of the extracted solution text (SKILL.md).
  • [COMMAND_EXECUTION]: The skill uses standard shell commands for file organization and directory management.
  • Evidence: The orchestrator executes mkdir -p to create directory structures for documenting solutions based on detected categories (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 05:25 PM
Security Audit — agent-trust-hub — ce-compound