repo-fleet-standardization
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it is instructed to read and honor instructions found within the external repositories it audits.
- Ingestion points: Processes repository files, READMEs, manifests, and local agent instructions from repositories across the fleet (SKILL.md).
- Boundary markers: Absent; the skill does not define specific delimiters to isolate external repository content from its core instructions.
- Capability inventory: File system write access (standardization fixes), execution of developer tools (jq, shellcheck, bash), and remote metadata mutation via the GitHub CLI (gh).
- Sanitization: Absent; the skill does not specify filtering or escaping mechanisms for the data ingested from audited repositories.
- [EXTERNAL_DOWNLOADS]: The skill performs a network request to fetch a validation schema from a well-known service.
- Evidence: Performs a check against
https://skills.sh/schemas/skills.sh.schema.jsonto validateskills.sh.jsonfiles. This is a well-known service associated with the skill's deployment environment.
Audit Metadata