companify-business-plan

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill reads multiple markdown files from the workspace to synthesize a consolidated business plan, which could allow malicious instructions in those files to influence agent behavior.\n
  • Ingestion points: Accesses approximately 15 different files including company/strategy.md, company/market.md, company/product.md, company/revenue.md, company/marketing.md, company/technology.md, company/operations.md, company/people.md, company/finance.md, company/ameacas.md, company/roadmap.md, .companify/assumptions.md, .companify/escolhas.md, and .companify/metrics.md.\n
  • Boundary markers: No explicit delimiters or instructions are provided to help the agent distinguish between the data it should summarize and the instructions it should follow.\n
  • Capability inventory: The skill is limited to file system read and write operations within the project directory. It does not possess network access or the ability to execute shell commands.\n
  • Sanitization: No input validation or filtering is performed on the content of the ingested files.\n- [NO_CODE]: The skill consists exclusively of markdown instructions and YAML configuration files. No executable scripts (Python, JavaScript, Shell) or binaries are included.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 11:34 PM
Security Audit — agent-trust-hub — companify-business-plan