demo-guide
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill includes instructions intended to override default agent behavior or platform constraints, such as "Ignore Claude-specific mode-switch instructions when they appear," "Strict execution contract," and "that skill activation authorizes use of the required spawn_agent subagent(s)."
- [PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by ingesting and processing untrusted data from local project files (source code, feature specifications, and git diffs) to generate its output. While it lacks explicit output delimiters for this data, it includes strong negative constraints against including sensitive information.
- [SAFE]: The skill implements security best practices for credential management by explicitly forbidding the inclusion of secrets, tokens, or connection strings in the generated demo guides, mandating the use of a
<redacted:…>placeholder for any sensitive values encountered during investigation.
Audit Metadata