memory-ci-capture

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized operations were detected in the skill instructions.
  • [PROMPT_INJECTION]: The skill processes data from a GitHub CI context file, which creates a surface for indirect prompt injection.
  • Ingestion points: Content is read from .github/basic-memory/project-update-context.json.
  • Boundary markers: Absent; the instructions do not explicitly direct the agent to ignore instructions that might be embedded in the source JSON.
  • Capability inventory: The skill's operation is limited to generating a specific JSON structure; it does not invoke shell commands, file system writes, or network operations.
  • Sanitization: No sanitization is defined, but the risk is low as the agent only generates a structured synthesis for another tool to process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 09:15 PM
Security Audit — agent-trust-hub — memory-ci-capture