Caveat verdict

ai-dev-engineer

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

Fetches from network AND uses eval/Function

This is a comprehensive reference workflow guide for AI application development covering prompt engineering, RAG, agents, deployment, and security — purely instructional content with no suspicious behaviors.

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
80
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 critical

Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)

LLM05 · LLM06 · ASI05

Capability combination critical

Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)

LLM01 · LLM05 · ASI01 · ASI05

Capability combination critical

Reads files AND uses eval/Function — may execute locally stored payloads

LLM05 · LLM06 · ASI05

Capability combination critical

Encodes data AND uses eval — the obfuscated-execution pattern (atob + eval; data-flow not verified)

LLM05 · ASI05 · ASI10

Capability combination critical

Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)

LLM02 · LLM06 · ASI03

Capability combination critical

Reads files, encodes data, AND makes external network calls — the obfuscated-exfiltration pattern (data-flow not verified)

LLM02 · ASI03

Permission integrity

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

network_out

Performs file operations but does not declare file-accessing binaries

file_read

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (4)

Pattern match high

Pipe to python — executes piped content as Python code

references/tech_stack_guide.md · prose · downgraded · | Python

Pattern match high

Prompt injection — tries to override agent instructions

scripts/guardrails.py · prose · downgraded · Ignore all previous instructions

Pattern match medium

POSTs data to external URL

references/safety_guardrails.md · code · .post( "https://

Pattern match medium

Possible prompt injection — attempts to redefine agent identity

scripts/guardrails.py · prose · downgraded · You are now

Permissions & capabilities

No declared permissions — minimal attack surface.

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