Caveat verdict
jira-openclaw
Accesses credentials AND makes external network calls
Jira integration skill with explicit secret-safe design using pastewatch redaction; credentials are stored in a local .secrets directory and curl calls target the user's own Jira instance, consistent with the stated integration purpose.
Automated static analysis โ 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 โ it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses credentials AND makes external network calls โ potential credential theft
LLM02 ยท ASI03
Accesses credentials AND encodes data โ may obfuscate stolen credentials
LLM02 ยท ASI03 ยท ASI04
Accesses credentials AND writes files โ may persist stolen credentials locally
LLM02 ยท LLM06 ยท ASI03
Permission integrity
network_out
file_read+write
credential_access
Findings (1)
Sets world-executable permissions
SKILL.md ยท code ยท chmod 700
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution โ cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions โ minimal attack surface.
file_writenetwork_outnetwork_incredential_accessdata_encoding Thanks โ recorded.