fast-track-ai-intent
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill is instructed to run a shell script located at
../fast-track-ai-init/scripts/fast-track-ai-index.sh. This execution occurs automatically during the indexing phase without explicit user confirmation for the command itself. Evidence: SKILL.md (Steps 8, 10, and 11). - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user requests and external sources, which could contain instructions designed to manipulate the agent.
- Ingestion points: User-provided text (Step 1) and content retrieved from external URLs or documents (Step 6).
- Boundary markers: None. While the skill uses Markdown templates, there are no instructions to delimit or ignore potentially malicious prompts within the external data.
- Capability inventory: The skill has the capability to write files to the local repository, execute shell scripts, and chain to other skills.
- Sanitization: No sanitization or validation of external content is specified.
- [EXTERNAL_DOWNLOADS]: The skill fetches content from URLs provided by the user to create 'inline' or 'pointer' reference artifacts. This ingestion of external data is a standard part of the skill's reference-tracking feature. Evidence: SKILL.md (Step 6).
Audit Metadata