Conference Talk Prepper
Analysis
This is a text-only conference speaking coach with no install steps, code, credentials, or evidenced autonomous actions; the only items to notice are low-risk provenance and capability-label ambiguities.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Source: unknown Homepage: none
The skill lacks public source or homepage provenance. Because the supplied package is instruction-only with no install spec or code, this is a minor review note rather than a supply-chain concern.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
- crypto - can-make-purchases
These registry-level capability signals are not clearly related to a conference talk preparation coach. The supplied artifacts do not show actual credential use, purchase authority, or crypto workflows, so this is a notice to verify capability boundaries rather than evidence of misuse.
