Caveat verdict

reflexion

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

This is a local agent learning system that captures errors and recalls past solutions from local files (.reflexion/entries/); agent_memory capability is the core declared purpose and executionSinkDetected reflects documented capture/recall shell scripts.

⚠ 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.

25
security
70
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (4)

Pattern match critical

Pipe to bash — executes piped content as shell commands

references/integration.md · code · | bash

Pattern match high

Pipe to python — executes piped content as Python code

scripts/capture.sh · prose · downgraded · | python3

Pattern match medium

References agent configuration files

SKILL.md · code · CLAUDE.md

Pattern match medium

Instructs covert action — may act without user awareness

scripts/recall.sh · prose · downgraded · silently

Why the tier is capped

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

agent_memorypackage_install

Is this flag fair?

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