kineti-pr-reminder
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill evaluates whether pull requests are eligible for reminders by analyzing unresolved threads and comment contents, which constitutes a vulnerability surface for indirect prompt injection.
- Ingestion points: The workflow retrieves pull request metadata and comment text via
gh apiand GraphQL as defined inSKILL.md. - Boundary markers: No delimiters or instructions are provided to help the agent distinguish between its own logic and content retrieved from GitHub.
- Capability inventory: The skill possesses the capability to execute GitHub CLI commands and send Slack direct messages to a list of predefined recipients.
- Sanitization: The skill does not implement sanitization or filtering of the ingested GitHub comment data before it is used in the decision-making logic.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands through the GitHub CLI (
gh api) to search for issues and retrieve repository-level metadata.
Audit Metadata