The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches the CLI binary and related tooling from the author's GitHub repository (github.com/mvanhorn/printing-press-library) and the NPM registry (@mvanhorn/printing-press).
[COMMAND_EXECUTION]: Relies on the Bash tool to execute the sec-edgar-pp-cli binary and manage the local SQLite database used for storage and analysis.
[DATA_EXFILTRATION]: Supports a --deliver webhook:<url> parameter that can route command output to arbitrary external URLs. It also contains a feedback reporting mechanism that can be configured to send local logs to a remote endpoint via the SEC_EDGAR_FEEDBACK_ENDPOINT environment variable.
[PROMPT_INJECTION]: Processes untrusted financial data from SEC EDGAR endpoints, creating an indirect prompt injection surface where malicious instructions embedded in public filings could attempt to influence agent behavior.
Ingestion points: Data is fetched from data.sec.gov and efts.sec.gov into a local SQLite store.
Boundary markers: None explicitly mentioned in the skill instructions to delimit external data from agent instructions.
Capability inventory: Full shell execution via the Bash tool and file reading via the Read tool.
Sanitization: No explicit validation or sanitization of the fetched SEC data is described.

pp-sec-edgar