course-description-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it ingests and processes untrusted content from external files to generate reports and modify project configuration.
- Ingestion points: The skill reads external content from
/docs/course-description.mdduring the Analysis Workflow (Step 2.1) to evaluate it against quality criteria. - Boundary markers: There are no instructions defining delimiters or boundary markers to isolate the analyzed content from the agent's core instructions, nor are there warnings to ignore embedded commands within the input file.
- Capability inventory: The skill possesses the capability to write new files (assessment reports), update metadata within existing files, and modify the project's
mkdocs.ymlconfiguration file based on the analysis results. - Sanitization: The instructions do not specify any sanitization, escaping, or validation steps for the data extracted from the course description before it is interpolated into metadata or used to trigger subsequent actions like modifying the navigation configuration.
Audit Metadata