The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from multiple external documentation files which could potentially contain malicious instructions intended to influence the agent behavior during strategic analysis.
Ingestion points: The skill reads data from .companify/company-context.md, company/market.md, company/business-model.md, and other executive analysis files in the company/ directory.
Boundary markers: No specific delimiters or 'ignore embedded instructions' warnings are implemented to separate the instructions from the data being processed.
Capability inventory: The skill's capabilities are restricted to reading and writing local markdown files within the workspace (company/strategy.md, .companify/progresso.md). No network access, remote code execution, or elevated system privileges were detected.
Sanitization: There is no evidence of content validation or sanitization for the data imported from external files.

companify-ceo