printing-press-score

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various shell commands via the Bash tool to perform setup and analysis. This includes using git rev-parse to determine the repository root, shasum to generate unique scope identifiers, and executing the cli-printing-press binary to generate scorecards.
  • [EXTERNAL_DOWNLOADS]: The documentation provides instructions to install a required dependency, the cli-printing-press binary, from the author's GitHub repository (github.com/mvanhorn/cli-printing-press). This is a vendor-owned resource necessary for the skill's primary function.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files and tool outputs, which could theoretically contain malicious instructions if the analyzed project is untrusted.
  • Ingestion points: Reads state.json and spec.json files within the workspace and project directories; parses JSON output from the cli-printing-press scorecard command.
  • Boundary markers: None explicitly defined in the instructions for the ingested data.
  • Capability inventory: The skill has access to Bash, Read, Glob, Grep, and AskUserQuestion tools.
  • Sanitization: The skill parses specific keys from JSON objects rather than interpreting raw text as instructions, reducing the risk of accidental execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:43 PM
Security Audit — agent-trust-hub — printing-press-score