pp-google-photos
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the 'google-photos-pp-cli' binary using 'npx' from the '@mvanhorn/printing-press-library' npm package and 'go install' from the 'github.com/mvanhorn/printing-press-library' repository. Both sources are associated with the skill's vendor.
- [COMMAND_EXECUTION]: The skill facilitates the execution of the 'google-photos-pp-cli' tool based on user-provided arguments to perform operations like searching media, creating albums, and managing authentication.
- [DATA_EXFILTRATION]: The skill includes features that allow sending command output to external URLs via the '--deliver webhook:' flag and POSTing local feedback entries to a server if the 'GOOGLE_PHOTOS_FEEDBACK_ENDPOINT' environment variable is set. These are documented features of the provided CLI.
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from the Google Photos API, such as album titles and media item descriptions, which are untrusted data sources that could contain hidden instructions for the agent.
- Ingestion points: Operations like 'google-photos-pp-cli media-items list', 'google-photos-pp-cli albums get', and 'google-photos-pp-cli media-items search' ingest data from the user's Google Photos library into the agent's context.
- Boundary markers: The skill encourages the use of the '--agent' flag, which forces structured JSON output, providing a clear data boundary.
- Capability inventory: The CLI can execute network requests to the Google Photos API, send data to arbitrary webhooks, and write files to the local system using the '--deliver' sink.
- Sanitization: No explicit sanitization or filtering of the API-returned metadata is mentioned in the skill instructions.
Audit Metadata