pp-elezioni-sicilia

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEDATA_EXFILTRATIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The elezioni-sicilia-pp-cli tool includes a --deliver webhook:<url> flag, which allows the agent to POST the results of election data queries to any external URL.
  • [DATA_EXFILTRATION]: The skill features a feedback command that can be configured via the ELEZIONI_SICILIA_FEEDBACK_ENDPOINT environment variable to automatically transmit local data logs to a remote server.
  • [EXTERNAL_DOWNLOADS]: The skill's installation instructions involve downloading binaries via npx from @mvanhorn/printing-press-library and go install from github.com/mvanhorn/printing-press-library. These are legitimate resources owned by the skill's author/vendor.
  • [COMMAND_EXECUTION]: The skill operates by executing shell commands using the elezioni-sicilia-pp-cli binary, passing arguments directly from user queries to the CLI.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests data from external election endpoints and possesses the capability to exfiltrate results.
  • Ingestion points: Election results and data tables fetched by the CLI from external Sicilian regional endpoints.
  • Boundary markers: No delimiters or safety instructions (e.g., "ignore embedded instructions") are defined for processing the ingested data.
  • Capability inventory: The CLI has the ability to write to files (file:<path>) and transmit data to external servers (webhook:<url>).
  • Sanitization: There is no evidence of sanitization or validation of the retrieved election data before it is displayed or delivered to external sinks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 09:18 AM
Security Audit — agent-trust-hub — pp-elezioni-sicilia