book-chapter-generator
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external files which could potentially contain malicious instructions intended to influence the agent's behavior during file generation and configuration updates.
- Ingestion points: Reads
/docs/course-description.md,/docs/learning-graph/learning-graph.json, and/docs/learning-graph/concept-taxonomy.md(SKILL.md, Step 1). - Boundary markers: The instructions do not define clear delimiters or provide warnings to the agent to ignore instructions embedded within the processed data.
- Capability inventory: The skill has the capability to create directories, write new markdown files, and modify the project's
mkdocs.ymlconfiguration (SKILL.md, Step 4). - Sanitization: There is no explicit requirement to sanitize or validate the content extracted from the input files before using it in file paths or configuration values.
- [COMMAND_EXECUTION]: The skill uses shell commands to manage the file system.
- Evidence: The skill instructs the agent to execute
mkdir -pto create the chapter directory structure (SKILL.md, Step 4.2).
Audit Metadata