bug-report-template
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process untrusted data to populate bug report templates. This includes informal prose (Step 1) and structured failure records like JUnit XML or Allure JSON (F1).
- Ingestion points: Data enters the agent context through the parsing of external files (e.g., JUnit XML, Allure JSON logs) and the extraction of raw evidence from user-provided notes or chat messages.
- Boundary markers: The instructions recommend using quotation marks for verbatim errors and markdown code blocks for stack traces. However, there are no robust delimiters or specific instructions for the agent to ignore embedded natural language commands within the processed data.
- Capability inventory: The skill parses files using standard libraries (e.g., Python's
xml.etree.ElementTree) and renders Markdown. It interacts with other agent skills to file reports but does not directly perform network or shell operations. - Sanitization: The skill lacks explicit sanitization or escaping protocols to prevent malicious instructions embedded in a bug report or log file from being interpreted as commands by the AI agent during the analysis or rendering phase.
Audit Metadata