ketchup

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple sources to generate progress summaries, creating a potential surface for indirect prompt injection.
  • Ingestion points: The skill collects work history, subagent reports, chat messages from other participants, and the state of external entities like Pull Requests (PRs) and CI runs as specified in SKILL.md.
  • Boundary markers: There are no specific delimiters or instructions provided to the agent to ignore potentially malicious embedded commands within the ingested data.
  • Capability inventory: The skill's actions are restricted to read-only operations and visual generation (Mermaid diagrams, screenshots). It contains explicit instructions in SKILL.md to avoid changing code, starting applications, or posting data.
  • Sanitization: The skill lacks explicit sanitization or filtering logic for the content it aggregates from external sources.
  • [EXTERNAL_DOWNLOADS]: The skill references resources from the cursor/plugins repository on GitHub in UPSTREAM.md. These references are documented for attribution and maintenance purposes and originate from a well-known development tool repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 01:47 PM