Caveat verdict

session-scribe

session-scribe-openclaw

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

Accesses credentials AND writes files

Reads local session transcripts and summarizes them via OpenAI/Anthropic API using a user-supplied key; explicitly warns about privacy implications, making the external-LLM data transfer fully transparent.

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.

50
security
60
transparency
70
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 writes files — may persist stolen credentials locally

LLM02 · LLM06 · ASI03

Capability combination medium

Both reads and writes files — verify scope is limited to intended directories

LLM06 · ASI02

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (2)

Pattern match low

Node http/https module — low-level network access

scripts/scribe.js · prose · downgraded · require('https')

Pattern match low

Accesses sensitive environment variables

scripts/scribe.js · prose · downgraded · process.env.OPENAI_API_KEY

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: OPENAI_API_KEY). Requires 1 system binary.

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