session-handoff

Fail

Audited by Gen Agent Trust Hub on Oct 31, 2026

Risk Level: CRITICALINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to audit workspace state and file changes, creating a surface for instructions embedded in data to influence behavior.
  • Ingestion points: Workspace files and metadata are ingested via git commands and file reads as defined in SKILL.md and context-hygiene-checklist.md.
  • Boundary markers: The skill does not define clear delimiters or "ignore embedded instructions" warnings for the content being audited.
  • Capability inventory: The agent has access to git commands and the filesystem for reading and summarization.
  • Sanitization: No sanitization or validation of the audited file content is performed before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The documentation contains links to external pages that were flagged as malicious by automated security scanners.
  • Evidence: Links to alapha888.github.io/mdclip-waitlist/, alapha888.github.io/agent-skills-pro/, and alapha888.github.io/syncmatrix-waitlist/ are included in README.md.
  • Context: While these appear to be promotional links for the author's other tools, the presence of security flags requires caution.
Recommendations
  • Contains 6 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Oct 31, 2026, 01:11 AM