sred-work-summary
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to determine the current year and locate local git repositories.
- Evidence:
date +%Y(Step 1) andfind . -maxdepth 2 -name ".git" -type d | sed 's/\/.git$//' | sort(Step 2). - Context: These are standard system operations used to scope the search for work items.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process large amounts of untrusted or external data which could contain malicious instructions.
- Ingestion points: The agent is instructed to read "the full document" for Notion documents and both "the title... and the description" for GitHub PRs and Linear tickets (Step 6).
- Boundary markers: Absent. There are no instructions provided to the agent to treat this external content as data only or to ignore embedded instructions.
- Capability inventory: The skill utilizes shell execution for local file discovery and MCP tools for reading/writing to GitHub, Notion, and Linear.
- Sanitization: Absent. The skill does not specify any sanitization, escaping, or filtering of the external content before it is processed by the model's logic for project grouping.
Audit Metadata