pr
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown templates and instructions designed to help an agent format pull request bodies. It does not request any tools, execute shell commands, or perform network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by instructing the agent to ingest domain-specific terminology from an external
GLOSSARY.mdfile. However, because the skill's capabilities are restricted to text generation and do not involve sensitive data or execution, the risk is negligible. - Ingestion points: The
GLOSSARY.mdfile is referenced in bothSKILL.mdandTRADUCAO.pt-BR.mdas a source for user domain language. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the glossary are provided.
- Capability inventory: The skill only generates markdown text for pull request summaries, evidence, and risk assessments. No execution-related tools or system access capabilities are present.
- Sanitization: No specific sanitization or validation of the glossary content is mentioned in the instructions.
Audit Metadata