export-open-issues
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests issue titles, labels, and metadata from external trackers (GitHub, Linear, Jira). If an issue contains malicious text designed to manipulate the LLM, it could alter the summary generation or analysis.
- Ingestion points: Fetches issue and PR lists via GitHub CLI, Linear MCP tools, and Jira queries in
SKILL.md. - Boundary markers: Absent; no delimiters or explicit instructions are provided to ignore potential command instructions embedded within issue fields.
- Capability inventory: Uses Bash commands (
date,mkdir -p) and repository CLI tools (gh). - Sanitization: Absent; text fields are processed directly without escaping or validation filters.
- [COMMAND_EXECUTION]: Executes system commands (
gh,date,mkdir) to fetch repository data and create local report directories. These operations are aligned with the primary functionality of the skill.
Audit Metadata