Ghostfolio
Analysis
This instruction-only skill is purpose-aligned for querying Ghostfolio, but it handles a long-lived portfolio token and may leave probe output locally.
Findings (3)
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.
For remote TLS diagnostics only, temporary `curl -k` can help.
The troubleshooting guidance mentions disabling TLS certificate verification. It is framed as temporary diagnostics, but using it with bearer tokens can weaken transport security.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
# Long-lived token supplied by user/admin export GHOSTFOLIO_TOKEN="..." ... AUTH_HEADER="Authorization: Bearer $GHOSTFOLIO_TOKEN"
The skill requires and uses a long-lived Ghostfolio token to access portfolio endpoints. This is expected for the stated purpose, but it is sensitive account authority.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
code=$(curl -s -o /tmp/gf_probe.json -w '%{http_code}' "$GHOSTFOLIO_BASE_URL$ep" \The quick probe writes API response bodies to a fixed temporary file, which may contain portfolio or error details and can persist after the command finishes.
