strategy-generate

Fail

Audited by Snyk on Nov 21, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate backtesting workflow, but its instruction to rerun after removing an extra delay and "report only the corrected run's metrics" could hide the earlier flawed run's results from the user, which fits the medium category of hiding the skill's own activity.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The only outsider-authored text is the parent strategy's description returned by get_strategy_evidence from the shared sdm: strategy registry, which the agent reads only after the user selects a specific strategy_id to adapt, so the agent must actively fetch it rather than receiving it from a monitored feed.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill mutates a shared strategy registry through adapt_strategy, refresh_strategy_evidence, and artifact_id bench-history recording, but no supplied operation or warning establishes irreversible loss of operational state, so the gate fails and the tier is capped at low.

Issues (3)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 21, 2026, 05:36 PM
Issues
3