duck-triage
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, which creates a surface for indirect prompt injection. Maliciously crafted bug reports or reproduction steps could attempt to influence the agent's triage results or severity classification.\n
- Ingestion points: The skill explicitly instructs the agent to collect and analyze evidence such as reproduction artifacts, logs, and failing paths (SKILL.md).\n
- Boundary markers: There are no specific delimiters or instructions to ignore embedded commands within the processed artifacts defined in the triaging workflow.\n
- Capability inventory: The skill uses the agent's general reasoning and reporting capabilities; no specific tool access or elevated permissions are requested in the YAML frontmatter.\n
- Sanitization: The skill does not include logic for sanitizing or validating the content of the external artifacts before they are analyzed.\n- [NO_CODE]: The skill consists entirely of instructional markdown and normative guardrails without any executable code or scripts, which limits the potential for direct technical exploitation.
Audit Metadata