Caveat verdict

adk

botpress-adk

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Accesses credentials AND makes external network calls

Botpress ADK is a documented TypeScript framework guide for building AI bots with conventional file-based structure; network and package capabilities are expected for a bot development SDK, and no exfiltration or malicious patterns are present.

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.

0
security
60
transparency
90
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (5)

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

SKILL.md · code · curl -fsSL https://github.com/botpress/adk/releases/latest/download/install.sh |

Pattern match critical

Pipe to bash — executes piped content as shell commands

SKILL.md · code · | bash

Pattern match medium

Popular HTTP library — network access

SKILL.md · code · got

Pattern match medium

Accesses sensitive environment variables

SKILL.md · code · process.env.API_KEY

Pattern match low

References agent configuration files

SKILL.md · prose · downgraded · agent-config

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/E). 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.

network_outnetwork_inpackage_installcredential_access
Check another skill Browse the registry Auditing your own skills or configs? Use the API