forge-all

Warn

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to read and follow a 'canonical playbook' from a relative path (../../../.fullstack-forge/skills/forge-all/SKILL.md) that escapes the immediate skill directory. This pattern allows for the execution of instructions stored in locations that may not be under the same integrity controls as the skill itself.
  • [COMMAND_EXECUTION]: The instructions explicitly direct the agent to execute shell commands forge doctor and forge update all if the installation is deemed damaged.
  • [PROMPT_INJECTION]: The skill description specifies that it should 'Activate automatically for repository-wide audits', which involves processing potentially untrusted data from a user's repository. 1. Ingestion points: Repository files and project structure (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Execution of 'forge' commands and file system access (SKILL.md). 4. Sanitization: Absent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 6, 2026, 06:48 PM
Security Audit — agent-trust-hub — forge-all