hyperframes
Warn
Audited by Snyk on Nov 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow never ingests outsider text by default; the registry search (SKILL.md line 16) returns community-published items the agent must select and fetch, and the website capture (line 14) fetches only a user-supplied URL, so both are low risk, while the bundled preset files are first-party assets.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The
initbranch (without--skip-skills) installs skills into the agent environment, a persistent agent-integration change, but no explicit irreversible operational loss appears in the supplied files, so the tier stays low.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata