fullstack-forge

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill relies on an external canonical playbook located at ../../../.fullstack-forge/skills/fullstack-forge/SKILL.md. The actual logic and instructions for the agent are contained in this external local file rather than within the skill package itself.
  • [COMMAND_EXECUTION]: The instructions mention the use of the forge command-line tool, specifically referencing maintenance commands such as forge doctor and forge update all.
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by instructing the agent to 'Read the canonical playbook now and follow it exactly' from an external path. This mechanism allows instructions outside the analyzed skill files to influence or override agent behavior.
  • Ingestion points: External local file ../../../.fullstack-forge/skills/fullstack-forge/SKILL.md (referenced in SKILL.md).
  • Boundary markers: None identified.
  • Capability inventory: Mentions execution of forge CLI commands.
  • Sanitization: None identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 06:48 PM
Security Audit — agent-trust-hub — fullstack-forge