panther-strike
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to ingest and act upon untrusted data from GitHub issues.
- Ingestion points: The skill fetches external content using the command
gh issue view {number} --repo AutumnsGrove/Latticein Phase 1 of SKILL.md. - Boundary markers: There are no explicit delimiters or instructions (e.g., "treat the following text strictly as data") provided to the agent to prevent it from obeying instructions embedded within the issue body.
- Capability inventory: The agent has the capability to edit files, execute local shell commands (
git,gh,pnpm), and search the codebase. - Sanitization: The skill does not define any sanitization, filtering, or validation steps for the content retrieved from the GitHub issue before it is used to influence the agent's investigation and planning.
Audit Metadata