standup
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing untrusted data from several sources.
- Ingestion points: Data is pulled from
git log, open PRs, meeting transcripts, and Slack threads as specified inSKILL.md. - Boundary markers: The instructions lack explicit delimiters or warnings for the agent to ignore potentially malicious instructions embedded in the processed data.
- Capability inventory: The skill has the capability to generate and format content for Slack, email, and other communication channels.
- Sanitization: There is no mention of sanitizing or escaping the input gathered from the codebase or external communication tools.
- [COMMAND_EXECUTION]: The skill executes
git log --oneline -20to retrieve commit history from the codebase. This is a standard read-only command used for gathering project context and does not pose a high risk of abuse in this context.
Audit Metadata