companify-cpo
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from several project files to generate its output, which creates a potential surface for indirect prompt injection if these files are sourced from untrusted parties.
- Ingestion points: Reads from
.companify/company-context.md,.companify/progresso.md,company/market.md, andcompany/business-model.md. - Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to ignore embedded commands within the source files.
- Capability inventory: The agent has the capability to read files and write the final strategy to
company/product.md. - Sanitization: There is no mention of escaping, validation, or filtering of the content read from the source files before it is processed by the agent.
- [SAFE]: The skill does not perform any network operations, remote code execution, or privilege escalation. All file operations are restricted to the local project environment.
Audit Metadata