retro
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of natural language instructions and Markdown formatting. It does not include scripts (Python, JavaScript, Shell) or configuration files that could trigger execution.
- [PROMPT_INJECTION] (SAFE): The instructions are focused on structured output for a retrospective. There are no attempts to override system prompts or bypass safety filters.
- [DATA_EXFILTRATION] (SAFE): No network calls, file system access, or credential patterns were detected.
- [REMOTE_CODE_EXECUTION] (SAFE): No external dependencies or remote script downloads are present.
- [PROMPT_INJECTION] (LOW): The skill ingests user input via the
$ARGUMENTSplaceholder to analyze a project or timeframe. While it lacks explicit boundary markers, the skill possesses no tools or executable capabilities that could be exploited via indirect prompt injection.
Audit Metadata