003-skills-inventory
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from a local file (
plinth-skills-generator/src/main/resources/skills.xml) to generate its output, representing a potential surface for indirect prompt injection. - Ingestion points: The agent reads the contents of
skills.xmlas specified inSKILL.mdandreferences/003-skills-inventory.md. - Boundary markers: There are no explicit instructions or delimiters used to separate the XML data from the agent's core instructions or to warn the agent to ignore prompts embedded within the data.
- Capability inventory: The skill's capabilities are limited to reading local files and creating/overwriting a Markdown file (
INVENTORY-SKILLS-JAVA.md) within the project directory. - Sanitization: The skill does not implement validation or sanitization of the input XML data before generating the markdown table.
Audit Metadata