one-bug-triage-prep
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill logic is focused on retrieving bug information via specified tools and formatting it according to a provided template. No high-risk operations or suspicious patterns were found.
- [PROMPT_INJECTION]: The skill processes untrusted data from bug titles and summaries, which presents a surface for indirect prompt injection.
- Ingestion points: External data enters the context through the output of
list-bugsandget-task-details(SKILL.md). - Boundary markers: None identified; instructions do not include specific delimiters to isolate external bug content from internal instructions.
- Capability inventory: No dangerous capabilities (subprocess execution, file system writes, or arbitrary network access) are available to the skill; its output is restricted to text generation.
- Sanitization: There are no explicit instructions to sanitize or filter the content retrieved from the bug tracker.
- Due to the lack of exploitable capabilities, this finding is considered safe.
Audit Metadata