What the reviewer found
Documentation for SafeClaw's Skill Scanner (a defensive static analyzer for AI skill files); every flagged string is an illustrative example of the malicious pattern the scanner itself detects (e.g. a sample hidden HTML comment, a sample curl|bash/rm -rf row in its own detection table), not an instruction the file carries out. This is the scanner's own reference material, harmless to install.
example-or-fixture— an example or test fixture
What was read
The file as it ships in DinoMorphica/safeclaw:
.claude/agents/skill-scanning.md
What the static scan said
The scan flagged 7things. The reviewer kept 0 and dismissed 7 as false.
P1Instruction-override phrasing — false positiveP2Hidden instructions — false positiveP6Asks the agent to reveal its instructions — false positivePE3Reaches for credential files — false positiveSC2Downloads and executes remote code — false positiveRMRecursive force delete — false positiveNETMakes network calls — false positive
How this review was made
Sonnet 5 read the files above on 7 September 2026 and answered three questions: is it dangerous to whoever installs it, is each scanner finding real, and what should the installer know. The verdict is bound to the file's hash; when the file changes, it is scanned afresh and reviewed again. A script that changes while the definition does not is not re-reviewed — that is a known gap. How the scan and the review work.