fix(skill): work around Claude Code permission prompt heuristics#66
Merged
AmethystLiang merged 1 commit intostablyai:mainfrom Mar 14, 2026
Conversation
Claude Code's permission checker has several security heuristics that
trigger manual approval prompts even when commands match allow rules.
This adds formatting rules to the skill and removes the hash prefix
from all channel name examples to avoid these triggers.
Triggers identified and documented:
1. Hash character anywhere in command string (treated as comment)
2. Consecutive quotes '' or "" (potential obfuscation check)
3. Pipe + mixed quote types (' and " in same command)
4. || or && chains with agent-slack commands
5. File redirects (>, >>)
See: anthropics/claude-code#34379
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
"#channel"examples with bare"channel"names across SKILL.md, commands.md, and targets.md#comments from code examples in targets.mdContext
Claude Code's permission checker has security heuristics that trigger manual approval prompts even when commands match
Bash(agent-slack search *)allow rules. After extensive testing, we identified 5 patterns that cause this:#anywhere in command string (e.g.--channel "#general")''or""(e.g..get('key', ''))| python3 -c "x = 'hello'")||/&&chains with agent-slack commands>,>>)Full findings: anthropics/claude-code#34379
Test plan