founder-context

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary function is to manage a local markdown file containing company facts. It does not perform unauthorized network operations or access sensitive system credentials outside of the intended project scope.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it interviews the user to populate the 'founder-context.md' file, which is intended to serve as a source of truth for downstream tools.
  • Ingestion points: User input via interactive interview rounds and project metadata (e.g., package.json) are ingested into the agent context.
  • Boundary markers: No explicit delimiters or boundary markers are defined for the user-supplied data in the file structure instructions.
  • Capability inventory: The skill is granted access to powerful tools including 'run_shell_command', 'write_file', and 'replace'.
  • Sanitization: The instructions include a specific security protocol requiring the agent to redact secrets and PII before sharing context with subagents and to treat external data as hostile.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 07:35 AM
Security Audit — agent-trust-hub — founder-context