pp-learn-disabled-example

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the CLI binary and supporting library from the author's official GitHub repository and npm organization (@mvanhorn/printing-press-library).
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests game resource data from external API endpoints which is then presented to the agent. Ingestion points: API results from listing games as described in SKILL.md. Boundary markers: The agent is instructed to use structured JSON output via the --agent flag. Capability inventory: The skill has access to the Read Bash tool and the CLI supports file writing and webhook POSTing via the --deliver flag. Sanitization: No explicit sanitization or validation of remote API content is documented.
  • [COMMAND_EXECUTION]: The associated CLI tool provides functionality to route command output to local files or external URLs using the --deliver sink feature.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 11:53 AM
Security Audit — agent-trust-hub — pp-learn-disabled-example