The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from financial reports, performance call transcripts, and shareholder letters retrieved from various third-party websites.
Ingestion points: The skill fetches raw materials from external sources including company IR pages, SEC EDGAR, Seeking Alpha, and other financial news platforms (SKILL.md).
Boundary markers: There are no explicit instructions or delimiters defined to isolate the ingested external content from the agent's instructions, nor are there warnings to ignore embedded instructions within that data.
Capability inventory: The skill has the capability to execute shell commands (running local Python scripts in the tools/ directory) and write files to the local workspace (saving reports in the reports/ folder).
Sanitization: No sanitization or filtering logic is mentioned for the content retrieved from external sources before it is processed by the agent or passed to the analysis tools.

earnings-team