Caveat verdict
grago
The skill explicitly states it executes shell commands and openly acknowledges that if the agent is compromised via prompt injection, Grago can execute arbitrary commands—this is an intentional but broad execution capability that significantly amplifies the prompt-injection attack surface.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (4)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
install.sh · prose · downgraded · curl -fsSL https://ollama.ai/install.sh | sh
Pipe to sh — executes piped content as shell commands
install.sh · prose · downgraded · | sh
Accesses shell history/config
install.sh · prose · downgraded · ~/.zshrc
Popular HTTP library — network access
README.md · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.