The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's documentation suggests executing local Python scripts (e.g., scripts/burn_rate_calculator.py) to perform financial calculations. These scripts are included in the skill distribution, use only standard library modules, and do not perform any risky system or network operations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data from files like company-context.md, which represents a potential surface for indirect prompt injection.
Ingestion points: Instructions in SKILL.md direct the agent to read company-context.md before responding.
Boundary markers: No explicit delimiters or markers are defined to isolate the ingested data from the agent's core instructions.
Capability inventory: The skill's tools are limited to financial analysis and math operations; it does not have access to the network, sensitive credentials, or administrative system commands.
Sanitization: No explicit sanitization or validation of the input data is described in the skill instructions.
[SAFE]: All external references and advice provided in the markdown files are consistent with established financial and startup management best practices. No suspicious URLs, obfuscated code, or hidden instructions were found across the skill files.

cfo-advisor