doc-consolidation
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads content from untracked markdown files (such as reports and analysis artifacts) and merges it into the repository's permanent documentation. This creates a surface for indirect prompt injection, as a malicious or compromised markdown file could contain instructions that the agent might obey during the consolidation process or that could influence future sessions when the documentation is read.
- Ingestion points: Untracked markdown files are identified and read in
modules/candidate-detection.mdandmodules/content-analysis.md. - Boundary markers: There are no explicit delimiters or "ignore embedded instructions" warnings defined to prevent the agent from following instructions found within the processed content.
- Capability inventory: The skill utilizes file system capabilities to write to files (
write_text) and delete source files (unlink) as described inmodules/merge-execution.md. - Sanitization: The skill lacks explicit sanitization, validation, or escaping of the extracted content before it is merged into the destination documents.
Audit Metadata