ai-slop-audit
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external, untrusted "artefacts" such as business plans, pitch decks, and source code provided by users.
- Ingestion points: The
SKILL.mdfile specifies the "artefact to audit" as a required input for the workflow. - Boundary markers: There are no explicit delimiters or specific instructions for the agent to disregard instructions embedded within the processed artefacts.
- Capability inventory: The skill involves reading, searching, and network operations to verify external links and dependency registries.
- Sanitization: The skill does not outline specific sanitization or escaping mechanisms for the data it ingests before performing analysis.
- [EXTERNAL_DOWNLOADS]: The skill references an external document to establish its "Shared standard" for publishing. The reference points to a markdown file on GitHub:
https://github.com/peterbamuhigire/chwezi-dev-engine/blob/main/references/ai-slop-responsible-publishing-standard-2026-09-11.md. This URL belongs to the skill author's repository and is used to define the audit criteria.
Audit Metadata