codealive-context-engine
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it retrieves and displays content from external repositories.
- Ingestion points: Code snippets and AI-synthesized explanations are ingested from the CodeAlive API in
scripts/search.py,scripts/chat.py, andscripts/explore.pywhich are then presented to the agent. - Boundary markers: While
scripts/search.pyuses textual headers (e.g., --- Result #idx ---), it lacks robust delimiters or explicit instructions to the agent to disregard potential commands embedded within the retrieved code. - Capability inventory: The skill can perform network requests to the vendor's API and interact with system credential managers via
subprocess.runto manage API keys. - Sanitization: Content fetched from the remote API is rendered to the agent without sanitization or filtering to remove potentially malicious instructions.
Audit Metadata