fcode-release

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the fcode CLI tool to manage application workspaces, specifically for cloning, adding remotes, pulling metadata, and pushing code. These actions are standard for the tool's intended deployment and release management purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads an external APP_VALIDATION_REPORT.md file to verify the health of the application before promotion. While this represents a data ingestion surface, the skill includes explicit instructions for the agent to seek user confirmation and provides logic to block automated actions if the report contains failures.
  • Ingestion points: APP_VALIDATION_REPORT.md referenced in the validation gate procedure.
  • Boundary markers: None explicitly defined for the validation report content.
  • Capability inventory: Workspace management and code deployment via fcode (clone, pull, push).
  • Sanitization: The skill relies on specific keywords (e.g., "Blockers") to parse the report rather than raw content interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 05:06 PM
Security Audit — agent-trust-hub — fcode-release