pp-discogs
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and install a CLI tool from the author's GitHub repository and NPM organization.
- Evidence: Commands
npx -y @mvanhorn/printing-press-library install discogs --cli-onlyandgo install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/discogs/cmd/discogs-pp-cli@latest. - [COMMAND_EXECUTION]: The skill functionality relies on executing the
discogs-pp-clibinary with various subcommands and flags. It also includes an output delivery feature that can write to local files or send data to webhooks. - Evidence: Usage examples for
discogs-pp-cliand the--deliver <sink>parameter documentation in SKILL.md. - [PROMPT_INJECTION]: The skill processes untrusted external data retrieved from the Discogs API, creating a surface for indirect prompt injection attacks where malicious instructions could be embedded in record metadata.
- Ingestion points: Data fetched from the Discogs database, marketplace listings, and user collections (SKILL.md).
- Boundary markers: There are no instructions provided to the agent to treat API-returned data as untrusted or to use specific delimiters.
- Capability inventory: The skill has the ability to write to the filesystem, make network POST requests via webhooks and feedback commands, and execute shell commands.
- Sanitization: The documentation does not describe any sanitization, filtering, or escaping of data retrieved from external API sources.
Audit Metadata