extract-glossary
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local or remote repositories to generate glossary and architecture documentation. A malicious repository could contain instructions designed to influence the agent's behavior during analysis.\n
- Ingestion points: The skill reads
README.md,docs/, code files, and schema files from user-specified repositories (SKILL.md).\n - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when reading external files.\n
- Capability inventory: The skill uses
rg(ripgrep) for searching,gitfor repository metadata, and has the ability to write multiple Markdown files and potentially perform git commits/pushes if requested.\n - Sanitization: No sanitization or filtering of the ingested content is specified before processing or output generation.
Audit Metadata