Template Discovery

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the WebFetch tool to retrieve README documentation and template configuration files from the to-be-continuous group on GitLab. These resources originate from a well-known service (gitlab.com) and are used to provide deterministic, verified examples to the user.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes and analyzes content fetched from external repositories.\n
  • Ingestion points: External YAML and Markdown files from GitLab are fetched and analyzed during the template discovery phases (SKILL.md, Phase 2).\n
  • Boundary markers: The skill does not explicitly utilize delimiters to isolate the fetched external content from its internal operational instructions during analysis.\n
  • Capability inventory: The skill's capabilities are restricted to conversational guidance and link provision; it lacks the ability to execute code, write to the filesystem, or access sensitive local data.\n
  • Sanitization: There is no evidence of explicit sanitization or filtering of the remote content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 12:05 PM