closing-obsolete-issues

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external GitHub issues and comments, creating a vector for indirect prompt injection where an attacker could influence the agent's behavior through crafted issue text.
  • Ingestion points: The scripts/fetch_issue_details.sh script fetches issue descriptions and comments from the flutter/devtools repository into the agent's context in SKILL.md (Instruction 2).
  • Boundary markers: The skill uses basic text headers such as "--- ALL COMMENTS ---" and "Description:" to separate fetched content, which are not robust against adversarial content meant to break out of data blocks.
  • Capability inventory: The agent has the capability to modify the local references/rationale_templates.md file and perform GitHub actions including posting comments and closing issues via the gh CLI.
  • Sanitization: No explicit sanitization, filtering, or instruction to disregard embedded commands in external text is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 03:14 AM
Security Audit — agent-trust-hub — closing-obsolete-issues