pp-offerup
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the download and installation of the offerup-pp-cli tool using npx from the NPM registry (@mvanhorn/printing-press-library) and go install from GitHub (github.com/mvanhorn/printing-press-library). These external resources are managed by the skill author.
- [DATA_EXFILTRATION]: The CLI includes a --deliver webhook: functionality that allows command results—which may include messages, account details, and marketplace data—to be sent to arbitrary remote servers. The skill also allows sending local feedback to an external endpoint via the OFFERUP_FEEDBACK_ENDPOINT environment variable.
- [INDIRECT_PROMPT_INJECTION]: 1. Ingestion points: Marketplace listing data (titles and descriptions) is retrieved from OfferUp and ingested into the agent context via search and get commands (SKILL.md). 2. Boundary markers: The instructions do not define clear delimiters or prompt the agent to ignore instructions embedded within listing text. 3. Capability inventory: The skill has the ability to execute terminal commands (via Read Bash), write to the local file system, and perform network requests to external webhooks. 4. Sanitization: No sanitization or validation of the untrusted listing content is performed before processing.
- [COMMAND_EXECUTION]: The skill functions by invoking the offerup-pp-cli binary within a bash environment.
Audit Metadata