companify-board
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and referenced documents do not contain any prompt injection attempts, obfuscation, or persistence mechanisms. Its behavior is consistent with its stated purpose of business analysis.
- [SAFE]: The skill reads files from the
company/and.companify/directories to perform its analysis. These operations are restricted to the local file system and do not involve unauthorized data exposure or external network communication. - [SAFE]: While the skill ingests content from external markdown files (a data ingestion surface), it lacks capabilities that would allow for exploitation, such as network access, system command execution, or dynamic code evaluation.
- Ingestion points: Business artifacts in the
company/directory. - Boundary markers: No explicit markers found.
- Capability inventory: Limited to file read and local markdown file writing.
- Sanitization: Not applicable given the limited capability set.
Audit Metadata