p-daily-standup
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources such as GitHub PR titles, Slack messages, and meeting transcripts to generate standup drafts.
- Ingestion points: Data enters through scripts and commands defined in
references/agent-gather-github-prev-day.md,references/agent-gather-slack-prev-day.md,references/agent-gather-fireflies-prev-day.md, andreferences/agent-gather-calendar-prev-day.md. - Boundary markers: The skill instructions do not explicitly define delimiters or instructions to ignore embedded commands within the fetched activity data.
- Capability inventory: The skill has the ability to post messages to Slack (
slack_send_messagein Phase 6) and modify its own configuration file (scripts/skillctx-resolve.py). - Sanitization: A human-in-the-loop confirmation step is enforced in Phase 6, requiring the user to review and approve the draft before any external action is taken.
- [COMMAND_EXECUTION]: The skill utilizes the
gh(GitHub) andgws(Google Workspace) command-line interfaces to retrieve activity logs. - [DYNAMIC_EXECUTION]: The skill executes a bundled Python script (
scripts/skillctx-resolve.py) to handle local configuration and binding resolution at~/.config/skillctx/config.json.
Audit Metadata