searching-sourcegraph

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or direct security threats were detected. The skill consists entirely of instructional Markdown documentation for code search workflows.
  • [NO_CODE]: The skill does not include any scripts or executable code, which eliminates the risk of direct command execution or local file system abuse.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process data from external codebases, which creates an attack surface for indirect prompt injection via malicious code comments.
  • Ingestion points: Data retrieved through Sourcegraph search tools like sg_read_file and sg_keyword_search across all provided workflow files.
  • Boundary markers: Absent; the instructions do not implement delimiters or warnings to ignore instructions found within the code being analyzed.
  • Capability inventory: The agent can search and read any file content indexed by the Sourcegraph instance.
  • Sanitization: Absent; the agent is encouraged to analyze and explain retrieved code content without prior filtering for instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 08:17 PM