standup-summary
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill accepts user-provided text for standup updates, creating an indirect prompt injection surface.\n
- Ingestion points: User input is mapped to JSON fields in the
run_jstool call as described inSKILL.md.\n - Boundary markers: Absent. The instructions do not explicitly direct the agent to ignore instructions that might be embedded within the user's status updates.\n
- Capability inventory: The skill's operations are confined to rendering a local HTML view. There are no file system access, network operations, or shell command execution capabilities present in
scripts/index.htmlorassets/webview.html.\n - Sanitization: The implementation in
assets/webview.htmlcorrectly uses.textContentfor all dynamic data insertion, which prevents cross-site scripting (XSS) even if malicious content is provided in the input fields.
Audit Metadata