kill-the-standup
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curland the GitHub CLI (gh) to interact with official APIs (Linear, GitHub, and Slack). These operations are essential to the skill's primary function and are performed using user-provided environment variables. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, specifically Linear issue titles and GitHub commit messages, which could theoretically contain malicious instructions.
- Ingestion points: Data enters the agent's context through GraphQL queries to Linear and REST API calls to GitHub in
SKILL.md(Step 2 and Step 3). - Boundary markers: The skill structures the data into a specific 'Done/Doing/Blockers' format before final processing.
- Capability inventory: The agent can execute shell commands (
curl,gh), write to temporary files, and perform network requests to Slack. - Sanitization: In
SKILL.md(Step 5), the skill mitigates command injection risks by using a heredoc with single quotes ('ENDJSON') to write the Slack payload to a temporary file. This prevents shell expansion or execution of any characters contained within the commit messages or issue titles.
Audit Metadata