Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent GEO prompt research helper that only generates local guidance or report files, with no hidden network, credential, or persistence behavior found.
Before installing, treat it as a local report generator: provide only business context you are comfortable putting into a report, and specify output filenames carefully because the script can overwrite the chosen destination. The advanced usage examples reference scripts that are not included in the artifact, so rely on the included research_prompts.py workflow unless you verify additional files separately.
The skill advertises executable workflows that write output files via commands like python scripts/research_prompts.py --output report.md, but it declares no permissions or allowed-tools scope. That mismatch can let an agent invoke file-writing behavior without an explicit least-privilege boundary, increasing the risk of unintended file creation or overwriting when the skill is auto-selected.
The description contains broad trigger phrases such as 'Use whenever the user mentions researching AI search queries' and similar generic research wording, which can cause the skill to match many ordinary requests beyond its narrow intended purpose. Over-broad invocation increases the chance of unnecessary execution of a skill with code/file-write behavior, potentially causing unintended actions or data handling in unrelated contexts.
No suspicious patterns detected.
