pp-edgar

Pass

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXFILTRATION]: The edgar-pp-cli tool includes a --deliver webhook:<url> feature, enabling it to POST command output directly to an external URL. Although the skill focuses on public SEC filings, this built-in capability allows the redirection of data to arbitrary network destinations.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as an ingestion point for external data by fetching SEC filings (via filings get, sections, etc.). This creates a vulnerability surface for indirect prompt injection if malicious instructions are embedded within the filing text. The skill lacks explicit boundary markers or instructions for the agent to sanitize or ignore instructions within the retrieved content.
  • [EXTERNAL_DOWNLOADS]: The instructions facilitate the installation of the edgar-pp-cli tool from the vendor's official resources using npx (from @mvanhorn/printing-press-library) and go install (from github.com/mvanhorn/printing-press-library). These downloads originate from the identified skill vendor.
  • [COMMAND_EXECUTION]: The skill requires the Read Bash tool to execute the edgar-pp-cli binary. It involves complex command patterns, including subcommands for full-text search, XBRL pivoting, and data delivery to local files or remote webhooks.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 02:42 AM