consolidate-strays
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill runs
node scripts/consolidate-strays.mjsto analyze the status of local skills and apply consolidation changes. - [REMOTE_CODE_EXECUTION]: It invokes
npx skillsto download and execute a distribution tool that synchronizes content with thehu3rror/my-skillsrepository. - [INDIRECT_PROMPT_INJECTION]: The agent is instructed to read file diffs and script outputs to manually populate rows in a
PATCHES.mdfile. - Ingestion points: File content differences between the local store and the aggregation repository.
- Boundary markers: The instructions lack explicit delimiters to protect the agent from instructions embedded within the files being processed.
- Capability inventory: The skill allows for local file modification and shell command execution.
- Sanitization: No mechanisms are provided to sanitize or escape the content of the diffs before the agent interprets them.
Audit Metadata