pp-slickdeals

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and installs the slickdeals-pp-cli tool and associated libraries from official vendor sources.
  • Evidence includes: npx -y @mvanhorn/printing-press-library install slickdeals --cli-only and go install github.com/mvanhorn/printing-press-library/library/commerce/slickdeals/cmd/slickdeals-pp-cli@latest.
  • These resources are owned by the skill's vendor (mvanhorn) and are standard for software distribution.
  • [REMOTE_CODE_EXECUTION]: The skill facilitates the installation and execution of external software via standard package managers (NPM and Go).
  • The go install and npx commands download and execute binaries from the vendor's infrastructure.
  • [COMMAND_EXECUTION]: The skill relies on the execution of the slickdeals-pp-cli binary to perform deal searches, analytics, and metadata management.
  • The agent is instructed to use the --agent flag for non-interactive execution, which is a best practice for automated skills.
  • [DATA_EXFILTRATION]: The CLI tool includes a built-in --deliver webhook:<url> feature that allows routing command results to an external HTTP endpoint.
  • While this is a functional capability of the tool for automation (e.g., syncing deal alerts to a user's service), it represents a potential data egress point that should be monitored.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external, untrusted content from Slickdeals RSS feeds and JSON endpoints.
  • Ingestion points: Slickdeals RSS feeds and featured-coupons JSON endpoints (SKILL.md).
  • Boundary markers: None explicitly defined in the instructions to separate external data from agent instructions.
  • Capability inventory: The skill allows for deal searching, thumb-count tracking, and merchant analytics using a local SQLite database.
  • Sanitization: No explicit sanitization or validation of the deal content (titles, descriptions) is specified before the agent processes the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 05:36 PM
Security Audit — agent-trust-hub — pp-slickdeals