Skills
Navigate
skills/peachest/skills/reckon/Gen Agent Trust Hub

reckon

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious prompt injection sequences.
  • Ingestion points: The scripts scripts/mr-state.sh and scripts/frontier.sh use the GitLab API to fetch titles and descriptions from Merge Requests and Issues.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish the fetched external data from the skill's own operational instructions.
  • Capability inventory: The skill possesses the ability to execute shell scripts that perform local file system operations (via git) and network requests (via glab).
  • Sanitization: No sanitization or escaping is performed on the data retrieved from GitLab before it is presented to the agent.
  • [COMMAND_EXECUTION]: The skill executes local shell scripts (scripts/position.sh, scripts/mr-state.sh, and scripts/frontier.sh) to perform its core functions, which include querying the Git repository state and interacting with GitLab instances via the glab CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 10:43 AM