pp-trustpilot
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of a CLI tool from the author's own NPM scope (@mvanhorn/printing-press-library) or GitHub repository.
- [REMOTE_CODE_EXECUTION]: The provided installation methods ('npx' and 'go install') involve downloading and executing code from remote sources to provide the skill's features.
- [DATA_EXFILTRATION]: The CLI includes a '--deliver' flag that can route output to external webhooks and a 'feedback' command capable of sending data to remote endpoints if configured.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill fetches external content such as Trustpilot reviews, business summaries, and AI topics via several search and fetch commands.
- Boundary markers: No instructions are provided to the agent regarding the use of delimiters to isolate untrusted review data from the prompt context.
- Capability inventory: The agent has permissions to execute Bash commands via a CLI that interacts with the network and local storage.
- Sanitization: The skill does not define any sanitization or validation processes for the data retrieved from Trustpilot before it is processed by the agent.
Audit Metadata