gh-depbot
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows security best practices by explicitly instructing the agent to never hardcode credentials or tokens in the
.github/dependabot.ymlfile. It correctly directs the agent to use GitHub Secrets syntax (${{ secrets.NAME }}) and advises users to configure these secrets in repository settings. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to read existing repository manifests (e.g.,
package.json,go.mod) and existingdependabot.ymlfiles to determine configuration needs. - Ingestion points: Reads manifest files such as
package.json,Cargo.toml,requirements.txt, and the existing.github/dependabot.yml(SKILL.md, references/config.md). - Boundary markers: None explicitly defined for the file contents, though instructions emphasize mapping file existence to ecosystem names.
- Capability inventory: Writes to the file system to create or update
.github/dependabot.yml(SKILL.md). - Sanitization: No specific sanitization of file content is described, but the logic is primarily structural (scaffolding YAML based on file presence).
Audit Metadata