forge

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes various forms of untrusted external data, creating an attack surface for indirect prompt injection where malicious instructions could be embedded in data sources.
  • Ingestion points: Repository text, fetched web pages, issue content, and tool output are ingested into the agent context.
  • Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate external data from the primary prompt instructions.
  • Capability inventory: The skill executes CLI commands (forge), manages local state files in .forge/, and routes to other functional engines.
  • Sanitization: The instructions explicitly mandate treating all external sources as untrusted and require revalidation of roots, revisions, hashes, and artifacts during every resume or verification step.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 07:33 PM
Security Audit — agent-trust-hub — forge