Caveat verdict
eval
Fetches from network AND uses eval/Function
This skill evaluates a personal assistant agent's health by reading local task files, checking calendar APIs the user has already configured, and scoring performance; it sources a local context file for known workspace variables and performs no exfiltration.
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.
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.
Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)
LLM05 · LLM06 · ASI05
Reads files AND uses eval/Function — may execute locally stored payloads
LLM05 · LLM06 · ASI05
Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 · LLM06 · ASI03
Accesses agent memory/notes AND makes external network calls — may leak personal data
LLM02 · LLM07 · ASI03 · ASI06
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Accesses agent memory AND makes external network calls — may leak conversation history
LLM02 · LLM07 · ASI06
Permission integrity
network_out
file_read
credential_access
agent_memory
Findings (1)
References agent memory files
SKILL.md · code · MEMORY.md
Permissions & capabilities
No declared permissions — minimal attack surface.
dynamic_evalcredential_accessagent_memoryfile_readnetwork_out Thanks — recorded.