Skills
Navigate
skills/reticlehq/reticle/fix-what-i-pointed-at/Gen Agent Trust Hub

fix-what-i-pointed-at

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text from an external interface (the Reticle HUD) to guide its operations.
  • Ingestion points: The note and fix fields within the marks data structure returned by the reticle_session tool.
  • Boundary markers: The instructions lack explicit boundary markers or directives for the agent to treat the note content strictly as data, potentially allowing embedded instructions to influence agent behavior.
  • Capability inventory: The skill is authorized to perform file system modifications (Open source.file at source.line), tool execution (reticle_act_and_wait), and session management (reticle_session).
  • Sanitization: No validation or sanitization of the input notes is mentioned.
  • [EXTERNAL_DOWNLOADS]: Fetches additional operational context from the vendor's documentation server.
  • Evidence: curl https://docs.reticle.sh/llms.txt in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 01:58 PM