ace-analysis

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the opencode command-line interface as a fallback method to retrieve session history in JSON format.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing session history, which is a potential surface for indirect prompt injection if previous messages contain instructions meant for the analyzer.
  • Ingestion points: Session data is retrieved from the session-read tool and the opencode CLI output (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters to isolate session content from the analyzer's primary logic.
  • Capability inventory: The skill has access to session reading tools and local CLI execution for data retrieval (SKILL.md).
  • Sanitization: No specific sanitization or filtering of the ingested session content is mentioned prior to the analysis phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 04:35 AM
Security Audit — agent-trust-hub — ace-analysis