The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process data from external, untrusted sources which could theoretically contain malicious instructions.
Ingestion points: Data is retrieved using WebSearch, WebFetch, and get_sec_filing as detailed in Step 4 of SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing external content.
Capability inventory: The skill utilizes several data retrieval tools (e.g., get_financial_statements, get_daily_prices, get_economic_indicator) and references a document generation skill (docx/SKILL.md) for output.
Sanitization: There are no instructions for sanitizing or validating the content retrieved from external sources before it is processed by the agent.
[SAFE]: The skill focuses on logical reasoning, financial calculations, and data extraction from official filings. It does not contain any executable scripts, obfuscated code, or unauthorized network operations.

impact-analysis