afk-to-tickets
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data by fetching content from user-provided URLs or reading local project specifications.\n
- Ingestion points: SKILL.md (Step 1) instructs the agent to fetch references and read their full body and comments.\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.\n
- Capability inventory: SKILL.md (Step 5) performs local file writes and network operations to publish issues to external trackers.\n
- Sanitization: No explicit sanitization or filtering of the external content is defined.\n
- Mitigation: The risk is mitigated by a mandatory human-in-the-loop review step in SKILL.md (Step 4), where the user must approve the ticket breakdown before execution.\n- [DATA_EXFILTRATION]: The skill performs network operations to fetch data and publish content to well-known external services such as GitHub and Linear (SKILL.md, Step 5). These actions are documented neutrally as they are essential to the skill's primary functionality and occur only upon user confirmation.\n- [NO_CODE]: The skill consists of instructional markdown and configuration files without including any executable scripts or binaries.
Audit Metadata