devops-specialist
Fail
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
references/domains/github-platform/core/setup/scripts/bash-aliases.shusescat >> "$BASHRC"to modify the user's shell configuration file (~/.bashrc) without explicit user intervention beyond running the command. Modifying persistent shell profiles is a high-risk persistence mechanism. - [EXTERNAL_DOWNLOADS]: The
gh-bootstraptool (defined inreferences/domains/github-platform/bootstrap/SKILL.md) clones numerous third-party GitHub repositories that are not from trusted organizations (e.g.,stevemao/github-issue-templates,dec0dOS/amazing-github-template,othneildrew/Best-README-Template). These downloads occur at runtime and are used to populate the user's local repository. - [REMOTE_CODE_EXECUTION]: The
gh-bootstrapexecution logic inreferences/domains/github-platform/bootstrap/phases/04-execution.mddownloads templates and then uses the agent toReadandWritethem into the local project. This includes generating GitHub Actions workflows (.github/workflows/*.yml), which are executable CI/CD scripts. This pattern effectively executes remote configuration from untrusted sources. - [PROMPT_INJECTION]: The file
references/domains/github-platform/core/setup/references/bashrc-claude.shdefines and promotes the use of shell aliases likeclaude-yoloandclaude-cont-yolowhich include the--dangerously-skip-permissionsflag. This encourages bypassing built-in safety prompts and security controls. - [INDIRECT_PROMPT_INJECTION]: The bootstrapping workflow demonstrates a significant vulnerability surface for indirect prompt injection:
- Ingestion points:
references/domains/github-platform/bootstrap/phases/04-execution.md(Downloads and reads content from untrusted external repositories). - Boundary markers: Absent. The tool is instructed to copy content "exactly as is" from the templates.
- Capability inventory: The skill uses
Bashfor cloning andWritefor creating files in the local environment. - Sanitization: Absent. There is no validation or filtering performed on the content retrieved from the untrusted third-party repositories.
Recommendations
- AI detected serious security threats
Audit Metadata